// SUPPORT REQUEST TRIAGE

FROM EMAIL TO
VERIFIED TICKET.

SRM is the Delaware Dept of Corporations support triage workflow. Paste an inbound email, SRM auto-creates the ICISTWO JIRA, asks the AI for the 6-field issue summary, assigns it to one of 55 developers, drafts the request-update + follow-up + verification messages, and logs every step. Five steps, one screen, full audit trail. Or skip the wizard entirely with One Shot — paste the email and get 8 AI-generated outputs in parallel, then create or update the JIRA with a single click.

Launch App Review Board Learn More
5
Workflow Steps
55
Developers Tracked
5,000+
Jiras Indexed
8
One Shot AI Outputs
// HOW IT WORKS

Six Stages. One Unified Workflow.

Every support request moves through the same six stages — from JIRA ticket creation all the way through team reporting. Each stage is atomic, logged, and resumable from the history tab.

01
Create JIRA
A JIRA ticket ID is entered as the entry point; the ticket is fetched via the Jira REST API and its metadata pre-populates the workflow.
02
Input Details
Request description, requester, urgency, and system are captured in a structured form, with the raw email body as the source of truth.
03
AI Analysis
Claude Haiku analyses the request, applies keyword routing, classifies complexity, and suggests assignees ranked by domain expertise.
04
Assign & Route
A developer is selected from the ranked suggestions; the request enters the tracking queue and the JIRA ticket is updated automatically.
05
Review & Approve
The review board processes pending requests with accept/reject actions and AI rewrites; skip logic prevents double-handling across sessions.
06
Report & Measure
Team performance, developer workload, and analytics reports surface velocity trends, resolution times, and queue health over time.

Triage Cockpit

One screen, three columns: paste the email on the left, watch the AI fill in the 6-field summary in the middle, see assignments and verifications track on the right. A 5-step stepper at the top walks you through Create JIRA → Input → Analyze → Assign → Verify so you never lose your place. Stat tiles show analyzed today, assigned today, verified today, and currently open.

meltuc.tech/srm/app
7
Analyzed Today
5
Assigned Today
3
Verified Today
12
Currently Open
1
2
3
4
5
Email Input
From: jessica.wurzel@delaware.gov
Subject: Cannot access portal

The corporate registration portal returns a 500 error this morning...
Analyze & Generate
Assignment
Gino Y Ortega
ICISTWO-35918
Assign
Update
JIRA Summary Output
PRIORITY LEVEL: High
Issue Title: Cannot access portal
TLDR: User Jessica Wurzel cannot access the corporate registration portal — receiving 500 error.
Stakeholders:
  Jessica Wurzel <jessica.wurzel@delaware.gov>
  Gino Y Ortega
JIRA Ticket: ICISTWO-35918
Assignment Message
Assigned ICISTWO-35918 to Gino, User cannot access the corporate registration portal — receiving 500 error.
History (12)
Apr 13 8:30amanalyzed
Apr 13 8:12amassigned
Apr 13 7:55amverified
Apr 12 5:40pmverified
Apr 12 4:22pmassigned

One Email. Eight Outputs. Instantly.

One Shot is a speed lane alongside the 5-step wizard. Paste one email, hit Process, and six parallel AI threads generate eight outputs simultaneously — JIRA summary, email summary, TL;DR, executive comment, assignment message, request update, follow-up, and verification draft. Each field shows a source tag (email-extracted, form override, system default, or user-edited) so you know exactly where every value came from. When you're ready, Create JIRA builds the ticket in one call; Update JIRA pushes all fields at once; Update JIRA Partial lets you selectively toggle which fields to push.

meltuc.tech/srm/app/oneshot
AI Model: Claude Haiku 4.5
Priority: High
Developer: Gino Y Ortega
JIRA: ICISTWO-35918
From: jessica.wurzel@delaware.gov
Subject: Cannot access portal — 500 error this morning
The corporate registration portal returns a 500 error for all users since approximately 8am...
⚡ Process
JIRA Summary email
Cannot access portal — 500 error — all users affected
Email Summary default
User reports platform-wide 500 error on the corporate registration portal since 8am.
TL;DR default
Portal 500. All corporate users blocked. Began 8am. Priority: High.
Exec Comment default
IT is aware of the portal outage. Gino Ortega is investigating. ETA TBD.
Assignment override
Assigned ICISTWO-35918 to Gino, portal returning 500 for all users since 8am.
Request Update default
Hi Gino, can you share a status update on ICISTWO-35918? The user is still blocked.
Follow-Up default
Following up on 35918 — still no resolution noted. Any blockers on your end?
Verification default
Hi Jessica, the portal issue has been resolved. Could you verify access is restored?
+ Create JIRA
↻ Update JIRA All
⋯ Update JIRA Partial
Generated in 2.1s (6 threads)

Live JIRA Charts

The Analytics tab pulls live counts straight from JIRA via JQL and renders two charts: a doughnut of Support Request tickets by status, and a horizontal bar of tickets per developer (top 15). Date range pills toggle Today / This Week / This Month / This Year so you can see what landed in the last 8 hours or what closed all year. The exact JQL is shown in the header for full transparency — no black box.

meltuc.tech/srm/app/analytics
Today
This Week
This Month
This Year
665 Support Requests
By Status
Resolved 402 Closed 149 Open 97 In Progress 16
By Developer (top 5)
Srinivas T.
182
Ashwin N.
131
Nitin P.
73
Cesily W.
59
Jaya P.
58

Full Audit Trail

Every analyzed request lives in a filterable history with status badges, priority labels, assigned developer, JIRA number, and creation date. Filter by status, developer, or free-text search across the email content, summary, JIRA number, or issue title. CSV and JSON exports for compliance reporting; ShipLog entries for cross-app tracking.

meltuc.tech/srm/app/history
Search title, summary, JIRA...
All Statuses
All Developers
JIRATitleDeveloperStatusDate
35918Cannot access portalGino Ortegaverified8:30am
35917Filing wizard 500 errorAshwin Nampallyassigned7:42am
35916Reports timeout on UAT2Cesily WatersverifiedApr 12
35915Bulk import schema mismatchSrinivas TopojianalyzedApr 12

Bulk Rewrite Pipeline

JIRA tickets created outside the SRM workflow often miss the Delaware 6-field format. The Review Board fetches all Support Request tickets via JQL and lets you run the AI rewrite pipeline across hundreds of tickets in one session. Auto-Run mode with smart skip zips instantly past tickets with no MSG attachment or already-processed descriptions, firing the configured delay only after a successful rewrite. A live banner tracks progress (done / total — ok, skipped) and an error log captures failures without stopping the run.

meltuc.tech/srm/app/review-board
Auto Run Active 47 / 812 — 44 ok, 3 skipped
Stop
Latest
ICISTWO-35971 Support Request MSG
Auto Accept
Auto Run
5s
Original Description
User reports intermittent 500 errors on the filing wizard. Assigned to Ashwin. Please investigate.
AI Rewrite — Proposed
PRIORITY LEVEL: High
Issue Title: Filing wizard 500 error
TLDR: Intermittent HTTP 500 on the filing wizard preventing document submission.
Stakeholders: Jessica Wurzel <jessica@...>
Accept description
Skip

Developer & Team Reports

Two full-featured performance reports built on live JIRA data. The Developer Report profiles a single assignee — ticket volume, resolution speed, priority distribution, status breakdown, and recent activity — with HTML and PDF export. The Team Report covers the whole roster across any custom date range: workload heatmap, period-over-period comparison, top performers, and per-developer drill-downs with direct cross-links to the Developer Report. The Head-to-Head report duels any two developers across 7 weighted metrics scored out of 10, rendered with radar and bar charts and a factual narrative summary. Team vs Team extends that to multi-developer groups — pick saved digest teams or build ad-hoc squads and compare aggregated performance side-by-side with a per-member breakdown.

meltuc.tech/srm/app/reports/team-performance
Team Performance — Apr 1–17, 2026
Export PDF
Export HTML
247
Tickets Closed
18
Active Devs
2.4d
Avg Resolution
↑12%
vs Prior Period
Workload Distribution
Srinivas T.
42
Ashwin N.
31
Cesily W.
24

Manager-Grade Developer Dossiers

The Developer Profiles feature gives a bird's-eye view of every developer's SR performance in a single screen — no report to generate, no date range to configure. Profiles are materialized from live JIRA data and cached: page loads are instant, zero Jira calls. A Top Performer spotlight band anchors the grid, followed by a dense ranked table (YTD closed, lifetime, open queue, resolution rate with inline bar, median TTR). Clicking any row opens a full dossier: an 8-cell stat grid with team-median deltas, an AI professional summary (3 grounded paragraphs from MiniMax, regenerated only when underlying stats change), a Milestones rail, a hand-rolled SVG monthly throughput chart, and a Recent SRs table. The roster is self-maintaining — new assignees appear automatically on the next Refresh All. Token-efficient: unchanged developers cost zero LLM tokens on refresh.

meltuc.tech/srm/app/profiles
SR
🏆 Top Performer — Ranked by YTD Closed
Srinivas T.
42
YTD Closed
187
Lifetime
91%
Res. Rate
18h
Median TTR
#DeveloperYTD ↓LifetimeOpenRes. RateTTR
1 Srinivas T. 42 187 3
91%
18h
2 Ashwin N. 31 142 7
78%
24h
3 Cesily W. 24 98 2
83%
21h
Cache-backed — zero Jira calls on page load • Roster self-maintains • AI narrative regenerates only when stats change

SLA Deadlines, Live

Every ticket gets an SLA deadline the moment it's created, computed from its priority level: P0 = 4 hours, P1 = 8 hours, P2 = 24 hours, P3 = 72 hours. The dashboard SLA panel shows hours remaining for every open request. Breached tickets appear in red so triage is instant — no spreadsheet cross-referencing required.

meltuc.tech/srm/app — SLA Panel
SLA Status — Open Requests
P0 Cannot access portal — 500 error ⚠ BREACHED +2.4h SLA: 4h
P1 Filing wizard 500 on UAT2 ⏱ 1.6h left SLA: 8h
P2 Reports timeout — ICISTWO-35916 ⏱ 18.2h left SLA: 24h
P3 Bulk import schema mismatch ⏱ 61.1h left SLA: 72h

Escalate to ServiceNow in One Click

When a support request needs to escalate beyond JIRA, the 🎫 Escalate to SNT button on any ticket detail inserts a record directly into snt_ticket_requests. The cross-app link appears instantly — no context switching, no manual data entry.

meltuc.tech/srm/app — Ticket Detail
ICISTWO-35918
Cannot access portal — 500 error
🎫 Escalate to SNT
✓ Escalated to SNT — ticket inserted into snt_ticket_requests

Keyword Frequency Cloud

The Word Bubble scans all 5,000+ ICISTWO Support Requests, tokenises every description, and builds a live word-frequency cloud. Spot recurring themes — which errors, modules, or user complaints dominate the queue — at a glance. Incremental rescanning skips unchanged JIRA entries so subsequent runs complete in seconds. Click any word to drill into the JIRA tickets that contain it.

meltuc.tech/srm/app/word-bubble
4,650 words indexed from 5,000 Jiras — Last scan: Apr 17 2026
Incremental Scan
Full Rescan
access portal login error timeout filing certificate cannot wizard 500 reset password database permission user report
// KNOWLEDGE BASE — RECURRING PROBLEMS

Pattern Intelligence, Not a Fix Manual

Delaware's developers don't write down how they fixed a ticket — so the Knowledge Base doesn't pretend to be a solution base. Instead it turns 5,000+ ICISTWO Support Requests into pattern intelligence and prediction: it tells you what problems keep coming back, who they hit, how often, the priority mix, and how long they take to resolve. The Recurring Problem Dashboard groups semantically-similar tickets into stable problem types, each with a 3-month trend, a predicted next-month volume, the typical owner, the priority mix, the median time-to-resolve (TTR), and a velocity rank that floats the fastest-accelerating problems to the top. Clusters keep the same identity run-to-run, so a trend means something.

meltuc.tech/srm/app/kb/recurring
11
Problem Types
4,820
SRs Indexed
3
Accelerating
02:14
Last Cluster Run
Problem TypeCountTrendPredictedTypical OwnerMed. TTR
Portal 500 / access errors412↗ up~38Gino Ortega18h
Filing wizard submission fails287↗ up~26Ashwin Nampally24h
Password reset / login241→ flat~22Cesily Waters6h
Report timeout on UAT2176↘ down~9Srinivas Topoji31h
Predicted = least-squares slope over trailing 6 months + mean of last 3 • Clusters carry stable IDs across runs • Click any row to drill into the problem type

Click any problem type to open its detail page: an AI-written 3-6 word label and one-line description (generated locally by qwen3, regenerated only when membership changes), a hand-rolled SVG monthly-throughput chart, the priority mix, the typical owner, the median TTR, and the full member-ticket table. The label and summary are grounded strictly on the member tickets — no invented solutions.

// KNOWLEDGE BASE — SIMILAR TICKET FINDER

Paste a Ticket. See What to Expect.

Drop in a Jira key (e.g. ICISTWO-35918) or paste free text describing a new issue, and the Similar Ticket Finder runs a vector similarity search across every embedded Support Request, returning the closest past tickets ranked by cosine similarity. Weak matches below 55% are hidden, and the ticket itself is excluded. Above the results sits a context card that summarises the matched set into a "what to expect" snapshot — how many times this has occurred, the median time-to-resolve, the typical owner, the priority mix, and when it was last seen. It tells you what to brace for, not the steps to fix it.

meltuc.tech/srm/app/kb/similar
ICISTWO-35918 —or— paste issue text...
🔍 Find Similar
Context — What to Expect
23
Occurrences
18.4h
Median TTR
Gino O.
Typical Owner
High×14
Priority Mix
Apr 12
Last Seen
JIRASummaryOwnerMatch
35610Portal returns 500 on loginGino O.91.2%
34188Cannot access registration portalCesily W.87.5%
33902500 error after SSO redirectGino O.72.1%
Matches below 55% are hidden<55%
// MANAGER DIGEST

Weekly AI Digest for Managers

The Manager Digest generates a structured weekly team report from live JIRA data and emails it directly to the manager via AgentMail. Configure the recipient, optional CC addresses, custom date range, and which sections to include — team summary, per-developer cards, aging open tickets, or AI highlights. Team groups let you scope the digest to a subset of developers (e.g. state-side vs. EPAM). Schedule it to fire automatically every Monday at 9am, or generate and send on demand. A full history log tracks every sent digest with period, developer count, ticket totals, and delivery status.

meltuc.tech/srm/app/reports/manager-digest
To: manager@delaware.gov
Team: State-Side
Apr 14 – Apr 18
📅 Schedule: Mon 9am
Send
47
Total Tickets
38
Closed
9
Still Open
9
Developers
ST
Srinivas Topoji State
12 tickets10 closed2 open
AN
Ashwin Nampally State
8 tickets7 closed1 open
CW
Cesily Waters State
7 tickets6 closed1 open
PeriodTeamDevsTicketsStatus
Apr 14–18State-Side947sent
Apr 7–11State-Side952sent
// WORKLOAD REPORTS

Queue Depth & Capacity

Two live workload views built on real-time JIRA JQL. The Team Workload Report shows open ticket counts per developer for a selected date range, surfacing imbalances before they become bottlenecks. The Developer Workload Report drills into a single developer — all open tickets, priority breakdown, and recent activity. Both export to CSV, HTML, or PDF and can be emailed directly from the report view.

meltuc.tech/srm/app/reports/team-workload
Team Workload — Apr 1–18, 2026
Export PDF
CSV
Email
18
Active Devs
94
Open Tickets
3
Overloaded
Open Ticket Distribution
Srinivas T.
16 ⚠
Ashwin N.
11
Cesily W.
7
Gino O.
5
// HEAD-TO-HEAD

Developer Head-to-Head

Pick any two developers, set a date range, and SRM computes a 7-metric weighted duel scored out of 10 points. Metrics include tickets resolved, SLA compliance, average resolution time, weighted workload, velocity, time to first action, and reopen rate. A radar chart and bar chart render the performance shape visually. A factual narrative summary names the winner and cites the two largest margin advantages — no AI required.

7 Metrics Weighted Scoring Radar + Bar Charts Live Jira Data
meltuc.tech/srm/app/reports/head-to-head
🏆 Ashwin Patel WINS 7.5 — 2.5 / 10
Ashwin Patel 🏆
7.5
out of 10
Marcus Webb
2.5
out of 10
Metric Ashwin Marcus Wt
↗ Tickets Resolved42 WIN282.0
↗ SLA Compliance94.2% WIN71.4%2.0
↘ Avg Resolution3.1 days WIN6.8 days2.0
meltuc.tech/srm/app/reports/team-vs-team
Side A
Alpha Squad
Ashwin Cesily James
vs
Side B
Bravo Force
Marcus Priya
🏆 Alpha Squad WINS 6.5 — 3.5 / 10
Developer Breakdown
Alpha Squad
Ashwin — 18 / 22
Cesily — 14 / 16
James — 10 / 13
Bravo Force
Marcus — 15 / 20
Priya — 9 / 14
// TEAM VS TEAM

Team vs Team

Extend Head-to-Head to multi-developer teams. Pick a saved team from the digest-teams roster or build an ad-hoc group by selecting any developers on the fly. Both sides can mix modes in the same comparison. Issues are aggregated across all team members and scored on the same 7 weighted metrics. A per-developer breakdown shows each member's individual resolved and total ticket counts.

Saved Teams Ad-hoc Groups Per-Member Breakdown 7 Weighted Metrics
// FEATURES

Everything in One Platform

Eleven integrated capabilities covering the full support request lifecycle — from intake and AI analysis through workload management, weekly manager digests, pattern intelligence, and cross-system escalation.

🎟️
Jira Integration
Auto-fetches ticket metadata (summary, priority, status, components) from the Jira REST API on entry. Create, update, and comment on ICISTWO tickets without leaving SRM.
🤖
AI Analysis
Claude Haiku classifies requests, applies SME routing by keyword, and ranks developer suggestions by domain expertise — returning the Delaware 6-field format every time.
📋
Review Board
Batch-process incoming requests with accept, reject, or AI-rewrite actions. Skip logic prevents double-handling and Auto-Run mode zips through hundreds of tickets in one session.
👥
Team Performance
15-section performance report covering velocity, resolution time, queue health, and period-over-period comparison across the full developer roster.
📊
Developer Reports
Per-developer breakdowns with avatar display, ticket counts, resolution rates, and workload heatmaps. Export to self-contained HTML or PDF via WeasyPrint.
⚖️
Workload View
Live workload distribution across the team with overflow detection and rebalancing suggestions. Cross-linked from the Team Report directly to Developer Report drill-downs.
🔗
SNT Integration
ServiceNow ticket generation triggered from SRM for cross-system incident escalation. One click inserts directly into snt_ticket_requests — no context switching required.
📈
Analytics Dashboard
Status distribution charts, developer velocity trends, and JIRA-linked metrics over configurable date ranges. Live JQL — no nightly sync, no stale cache.
📧
Manager Digest
Scheduled or on-demand weekly digest emailed to the manager via AgentMail. Per-developer cards, team summary, aging tickets, and AI highlights — scoped to custom teams.
⚖️
Workload Reports
Team Workload and Developer Workload reports surface open ticket distribution, overload flags, and capacity gaps. Export to CSV, HTML, or PDF; email direct from the report.
🧠
Knowledge Base
Pattern intelligence over every Support Request — a Recurring Problem Dashboard with next-month volume predictions and a Similar Ticket Finder. Surfaces what recurs and what to expect, not how to fix (devs don't document fixes).
// INSIGHTS HUB

Insights Hub

15 read-only analytics screens built on your ticket data

The Insights Hub delivers 15 pre-built dashboards that surface operational intelligence, strategic metrics, and pattern analysis from your Jira ticket history — no configuration required. Open any screen and the data is already there, drawn live from ICISTWO and organized into five categories so you always know where to look.

🚨
Operational Intelligence
Real-time risk signals across your open queue.
SLA Risk Board
Outbreak Detector
Response Gap Monitor
📊
Strategic Metrics
Long-horizon views for capacity planning and quality tracking.
Backlog Burndown
FCR Dashboard
Volume Forecasting
🔍
Pattern Mining
Temporal and requester-level patterns extracted from ticket history.
Pattern Calendar
Requester Pareto
Requester Journey
👥
Team Intelligence
Developer-level efficiency and skill signals across the full roster.
Resolution Velocity
Specialization Map
Complexity Scorer
📋
Executive
Board-ready snapshots and lifecycle analysis for leadership reviews.
Executive Snapshot
Duplicate Detector
Lifecycle Analyzer
// CAPABILITIES

Everything SRM Does

SRM bundles sixteen capabilities that used to be separate tabs, emails, and spreadsheets. Every action is atomic, every action is logged, and every step is rewindable from the history tab.

One Shot
Skip the wizard. Paste one email and get 8 outputs in parallel — JIRA summary, email summary, TL;DR, exec comment, assignment, request update, follow-up, verification. Source tags show email-extracted vs. override vs. default. Create or update JIRA in one click.
8 parallel outputsSource taggingPartial push
J
JIRA Integration
Direct Atlassian REST v3 connection to the Delaware ICISTWO project. Create tickets, patch descriptions, add comments — no copy-paste, no browser detour.
ICISTWOREST v3Basic Auth
5
5-Step Flow
Create JIRA → Input → Analyze → Assign → Verify. A persistent stepper highlights where you are and lets you jump backwards without losing state.
Stepper UIResumable
AI
AI Analysis
OpenRouter + Claude Haiku 4.5 reads the raw email and returns the locked Delaware 6-field summary: Priority, Issue Title, TLDR, Stakeholders, JIRA, Developer.
Claude Haiku 4.5OpenRouter
Auto-Assignment
Pick from the 55-dev roster or filter to the 9 state-side directs. SRM drafts the exact assignment message Delaware expects and patches the JIRA assignee in one click.
55 devsState-side filter
Verification Drafts
Paste the developer's resolution back in, SRM generates the "please verify" message to the original requester and flips the request status to verified.
Verify stepStatus: verified
Live Analytics
The Analytics tab hits JIRA with live JQL and renders real counts — no nightly sync, no stale cache. Date pills scope to Today / Week / Month / Year.
JQL live4 ranges
Developer Charts
Horizontal bar of Support Request tickets per developer (top 15) plus a doughnut chart of tickets by status. Answers "who has what" in one glance.
Top 15By Status
Status Tracking
Every request walks through analyzed → assigned → updated → verified. Full audit trail with filterable history, CSV / JSON export, and ShipLog cross-app entries.
Audit trailCSV + JSONShipLog
Review Board
Bulk AI rewrite pipeline for existing ICISTWO tickets. Auto-Run smart-skips no-MSG and already-processed entries at 0ms, fires the configured delay only after a successful rewrite. Bulk Accept applies the AI rewrite to up to 50 selected tickets in one call, with per-ticket success/failure reporting. Paginated across all 800+ Support Requests.
Auto-RunBulk Accept (50)Smart skip
Performance Reports
Developer Report (single assignee deep-dive) and Team Report (full roster, 15 sections, period comparison). Both export to self-contained HTML or PDF via WeasyPrint. Cross-linked: Team workload row links directly to Developer Report.
Dev ReportTeam ReportPDF export
Word Bubble
Indexes 5,000+ JIRA Support Request descriptions into a keyword frequency cloud. Incremental scanning skips unchanged entries. Click any word to drill into matching tickets. DB-backed state survives service restarts.
4,650 wordsIncrementalDrill-down
SLA Deadline Tracking
Every ticket gets an SLA deadline computed from its priority: P0 = 4h, P1 = 8h, P2 = 24h, P3 = 72h (windows are configurable per priority in Settings). The dashboard timer panel shows hours remaining per open ticket and highlights breaches in red, and on verify SRM syncs the JIRA due date to the SLA deadline. Never miss a service-level commitment.
ConfigurableJIRA duedate syncP2 24hBreach alerts
🎫
SNT Escalation
One-click escalation from any ticket detail to ServiceNow. The Escalate to SNT button inserts directly into snt_ticket_requests, then the SNT ticket id is linked back onto the SRM request for a bidirectional cross-app link — without leaving the SRM workflow.
Cross-appOne clickBidirectional link
📧
Manager Digest
AI-generated weekly team report emailed directly to the manager via AgentMail. Includes team summary stats, per-developer cards with ticket counts, aging open tickets, and optional AI narrative highlights. Scoped to custom team groups; schedulable on a weekly cadence.
AgentMailTeam groupsScheduledPDF export
Team Workload
Live JIRA JQL report of open ticket distribution across the full developer roster. Highlights overloaded developers and surfaces capacity gaps at a glance. Export to CSV, HTML, or PDF; email from the report view.
Open ticketsCapacity flagsCSV + PDF
📊
Developer Workload
Single-developer deep dive — all open tickets, priority breakdown, and recent activity for a specific assignee over a chosen date range. HTML/PDF export and direct email delivery.
Per-developerPriority mixPDF export
🧠
Knowledge Base — Pattern Intelligence
Two KB tools turn 5,000+ Jira Support Requests into pattern intelligence + prediction, not fix steps — developers don't document how they resolved tickets, so the KB surfaces what recurs, who it hits, how often, and what to expect. The Recurring Problem Dashboard shows each problem type's member count, 3-month trend, predicted next-month volume, typical owner, priority mix, and median time-to-resolve. The Similar Ticket Finder takes a Jira key or free text and returns past matches plus a context card. A nightly Kronos pipeline (scan → embed → cluster) keeps it current; failures raise a Herald alert and auto-trigger a re-run.
Recurring DashboardSimilar FinderVolume predictionNo fix steps
🚨
Resilient Alerting
Every failure mode — AI analysis, JIRA assignment, verification, and KB timeouts — emits a structured Herald alert with an error_code and context. Developer assignments also fire a real-time Telegram notification so the assignee knows the moment a ticket lands.
Herald alertserror_codeTelegram
// THE PIPELINE

5 Steps. Zero Friction.

Each support email goes through the same five-step pipeline. Skip steps you don't need. Reload from history any time. Every action is logged.

1. Create JIRA

Paste the email, click Create New JIRA. SRM extracts the Subject line, opens an ICISTWO ticket via the Atlassian REST API, and shows you the key + browse link.

2. Input

The pasted email body becomes the initial JIRA description. The form is now ready to analyze.

3. Analyze

OpenRouter (Claude Haiku 4.5) reads the email and returns the 6-field Delaware-format output: Priority, Issue Title, TLDR, Stakeholders, JIRA, Developer. The result is pushed back into the JIRA description.

4. Assign

Pick a developer from the 55-name roster (or filter to the 9 state-side direct assignees). SRM drafts the assignment message in Delaware's exact format.

5. Verify

Paste the developer's resolution email back into SRM. The AI generates a "please verify" message addressed to the original requester. Status flips to verified, ShipLog logs it, optional Telegram alert fires.

// THE AI OUTPUT

Delaware-Format Summary

Every Analyze call produces the same six fields, in the same order, in plain text ready to paste into ServiceNow or JIRA. Stakeholder rules respect dosdoc_supportrequests and dosdoc_tech_support exclusions automatically.

!
Priority Level
High / Medium / Normal / Low — Delaware levels (no "Critical").
T
Issue Title
The exact email Subject line, used as the JIRA summary.
TLDR
2–3 sentence narrative the developer sees first.
@
Stakeholders
Real humans only — generic distribution lists are stripped automatically.
#
JIRA Ticket
Auto-extracted from the analysis output and pushed back into the form.
D
Developer
Inferred from the email if mentioned; otherwise picked from the assignment dropdown.
// OUTBOUND DRAFTS

Four Drafted Messages

SRM does not send mail on your behalf — it drafts the four messages Delaware expects in their exact format so you can review, edit, and send from Outlook. Every draft is keyed to the active JIRA and logged in the request history.

Assignment Message

One-liner for the developer: "Assigned ICISTWO-##### to {Dev}, {TLDR}." Ready to paste into the assignment channel.

Request Update

Polite nudge to the assigned developer asking for a status check. Used from the dashboard between Assign and Verify.

Follow-Up

Second-touch reminder when a ticket has been sitting idle. Same JIRA context, different tone.

Verification Email

Addressed to the original requester, written in the requester's language. Confirms the fix and asks them to mark the ticket verified.

// DEVELOPER ROSTER

55 Devs. 9 State-Side.

SRM ships pre-seeded with the full Delaware Dept of Corporations IT roster: 55 developers total, 9 of whom are state-side (direct assignments). The remaining 46 are EPAM contract team and route through Srinivas Topoji. A toggle on the dashboard filters the dropdown to state-side only when you're routing direct.

Ashwin Nampally
Cesily Waters
Charles Loubao
Gino Y Ortega
Jaya Padigala
Melvin Tucker
Ronnika Johnson
Sam Ackah
Srinivas Topoji
// INTEGRATIONS

Wired Into The Stack

SRM does not try to be a system of record — it glues the ones you already have together. Every outbound call is rate-limited, credential-scoped, and logged.

A
Atlassian JIRA
REST API v3 against the ICISTWO project. Create, describe, assign, comment, and query via JQL. Credentials live in /root/.secrets, never in the repo.
CloudJQL
O
OpenRouter
Single endpoint brokering Claude Haiku 4.5 for analyze + verify. Temperature pinned low for format stability; retries on 5xx.
Haiku 4.5Low temp
T
Telegram
Optional push on verify — fires a one-liner to the MelTuc bot so you know the loop closed without tabbing back.
OptionalOn verify
S
ShipLog
Verified requests drop an entry into the cross-app ShipLog so the meltuc.tech dashboard sees SRM activity alongside every other blueprint.
Cross-app
// GET STARTED

Triage in Seconds. Verify in Minutes.

Every support email through one screen. JIRA, AI summary, assignment, verification, audit log — all in five clicks.

Launch Support Request Manager

Requires a MelTuc account. Create one free.