Shaduf.Research preview
Jev: Use Cases, Alternatives & Products/Support-ticket triage with Jev
Use casesFive projects read at pinned commits · paths that never ask Jev read at the same pins · failure terms aligned with the failure checklist

Support-ticket triage with Jev (TypeSafe AI): what real projects do when Jev fails, and a safe design

Routing support tickets to the right queue is a frequent concrete Jev use case: GitHub repository searches for "jev triage", "jev ticket" and "jev support" returned 272, 70 and 158 results on 1 Oct 2026, not all of them relevant. This page compares five public ticket-triage projects on one question: what happens to a ticket when Jev is unsure, returns an error, returns something malformed, has no key or hangs. Every cell comes from the project's source code at a stated commit. From that comes an eight-rule safe design.

Key finding

Four of five ticket-triage projects read in source send unsure tickets to a person. The fifth ignores queue confidence, and on any Jev API error it files the ticket in its archive lane.

Documentedsource at pinned commits, checked 1 Oct 2026

These are five projects out of at least 70 more triage repositories that were not read, so this is not a survey of how triage is usually built. None of the five takes a refund or account action from a Jev answer. None is independently verified as operating for real customers: two are helpdesk integrations (Zammad), three are demos or a command-line tool.

What happens to a ticket when something goes wrong

Open a situation to highlight its column in the table and read the safe pattern for it; opening one closes the others. Documented Read from source at the commits shown; README descriptions were not used.

Jev is unsureConfidence below the project's threshold

Four projects gate the queue choice on confidence and send the rest to a person: thresholds 0.5 (B), 0.55 (C), 0.6 (E) and 0.9 (D). A has no gate on its department choice: the chosen team is always used. Safe pattern: below your threshold, send the ticket to a person with the best guess and probabilities attached, as C does with an internal note.

API errorThe request fails with an HTTP error

Only D treats an error as "no decision": it returns 503, leaves the ticket unchanged and lets Zammad retry ("Never return a successful decision on model or API errors"). A files the ticket in its archive lane. B and C return 502 and leave the ticket unrouted (C without a note). E stops the whole batch. Safe pattern: hold the ticket for retry or a person; never map an error to a real queue.

Malformed answerMissing fields or values out of range

Only D validates the answer: the model id must match, the choice must be one of the options and the probability must be a finite number in [0, 1]. A does not validate, so a missing or non-numeric field ends in archive. B, C and E raise an error. Safe pattern: validate before acting and treat a failed check as an error.

No API keyThe key is not set

B, C and E refuse to start or exit. A returns HTTP 500 per request. D returns 503 so the source retries. All five fail visibly; none silently skips Jev. Safe pattern: fail loudly at start-up.

Jev hangsNo answer within a timeout

Two of five set no timeout (A uses a bare fetch, C uses HTTParty's default). D sets 20 s; B and E rely on the official SDKs' defaults. Safe pattern: set a timeout you chose, or know your SDK's defaults (see errors and rate limits).

Project (commit)Jev unsureAPI errorMalformed answerNo keyTimeoutSent to Jev
A. CyrilBaah/jev-triage-desk (63913177)Runnable demo (Next.js); direct fetch to /v1/systemone, jev-latest. Tests: noneno-threshold: no gateThe chosen team is always used; lanes by spam, escalate and urgency scoresfallback-archive laneException caught; reason "error"fallback-archive laneNo validation; a missing or non-numeric field ends therefail-closedHTTP 500. "TYPESAFE_API_KEY is not set"None setBare fetchTicket body. In the agent lane, subject and body also go to Groq for a draft reply
B. tuhinmitra888/ai-jev-ticket-triage (3e8b83a8)Runnable demo; official JS SDK @typesafe-ai/sdk. Tests: 6 policy tests, no networkheld: < 0.5 → human triageOption other → human toofail-closed: 502, not routed"triage failed"fail-closedThrows → 500. No runtime checkfail-closedServer does not start. Client built at module loadSDK defaultNot set in codeSubject, body; customer plan kept local
C. enderkus/zammad-jev-dispatcher (f999eca7)Zammad helpdesk integration; HTTP POST, jev-latest. Tests: noneheld: < 0.55 → stays "Unclassified"With an internal note: best guess and probabilitiesfail-closed: 502; stays UnclassifiedNo notefail-closedRaises → 502. Unknown choice → manual-triage notefail-closedDoes not start. Raises at bootNone setHTTParty defaultTitle and body, HTML stripped; customer not sent
D. gbesse/zammad-jev-triage (5d2a0a78)Zammad helpdesk integration; pinned model jev-1.13.0. Tests: 3 test files and CIheld: < 0.9 or other → reviewMapped to a review groupfail-closed: 503; source retriesTicket unchangedfail-closedValidated → 503. Model, option and probability checkedfail-closed503; source retries. 20 sSet explicitlyTitle and body, HTML stripped, at most 16,000 characters; public articles only
E. veermshah/jev-support-desk (aef8fa0c)Command-line tool; official Python SDK. Tests: 7 test files and CIheld: < 0.6 → triage reviewNoul answers in 0.35–0.65 flagged "uncertain"fail-closed: batch abortsExit code 2; one failure stops the runfail-closedRaises → exit. Typed SDK responsefail-closedExit code 2. SDK default10 s per attempt, 30 s budgetSubject and message; tier and routing metadata kept out
  • fail-closed or held (the item does not go ahead; a person, the host's prompt or, for two passage filters, the code's own cut decides)
  • fallback-<what> (named in the cell)
  • not recorded, not applicable or no-threshold (the cell says which)

Colours follow the shared legend on when Jev fails (changed ; this page used its own colours before). The Timeout column is a setting, not a verdict, so it is uncoloured.

What each project does automatically: A assigns a lane and shows an LLM-drafted reply (no send code found); B sets queue, priority and flags, and a refund request is only a flag; C and D change the Zammad group (C also posts an internal note); E sets labels and suggested actions only. Not one of the five refunds, cancels or changes an account from an answer.

Where each project draws the line

Queue-confidence threshold below which a ticket goes to a person

  • D. zammad-jev-triage0.90
  • E. jev-support-desk0.60
  • C. zammad-jev-dispatcher0.55
  • B. ai-jev-ticket-triage0.50
  • A. jev-triage-desknone
Bar length is the threshold on a 0–1 scale. C's threshold is set by the environment variable DISPATCH_CONFIDENCE_THRESHOLD (default shown). B also adds a review reason when urgency confidence is below 0.4. A routes on spam, escalate and urgency scores (lanes at 0.6, 0.6, 2.5 and 1.0) but never checks how sure Jev is of the department. How to choose your own is on confidence thresholds. Documented

Code paths that never ask Jev

In all 5 triage implementations every routed ticket goes through Jev; the skips we found (bad requests, already-dispatched tickets, non-customer replies, cached replays) route nothing new (read at pinned commits, 14 Oct 2026).

Documentedsource at pinned commits, read 14 Oct 2026; bypass recorded for 5 of 5

Bypass cells for the five projects. 3 have skip paths (zammad-jev-dispatcher, gbesse, jev-support-desk); for 2 the recorded cell is "none found" in the entry-point files read (jev-triage-desk, ai-jev-ticket-triage): 3 + 2 = 5. gbesse/zammad-jev-triage's HEAD has moved to f46e5ad since the pin (R16-S126); the cell was read at the pin.

Project (commit)Code paths that never ask JevWhere (file: lines)Source
CyrilBaah/jev-triage-desk 63913177recordednone found (only an empty-ticket 400 and the no-key 500, which route nothing)app/api/triage/route.ts L108–120R16-S100, R16-S127
tuhinmitra888/ai-jev-ticket-triage 3e8b83a8recordednone found (an empty or too-long ticket gets a 400)src/server.ts L11–16, L34–40R16-S101, R16-S102
enderkus/zammad-jev-dispatcher f999eca7recorded3 skips leave the ticket unrouted: no ticket, no destination groups, already dispatchedapp.rb L104, L107, L110R16-S103
gbesse/zammad-jev-triage 5d2a0a78recordedwebhook rejections (404, 413, 401, 400); non-customer and internal articles skippedwebhook.py L20–33; app.py L14R16-S104, R16-S105
veermshah/jev-support-desk aef8fa0crecordedcache replay reuses stored triages without a Jev callcli.py L31–32R16-S106, R16-S107
  • fail-closed or held
  • fallback-<what>
  • not recorded; for "Jev unsure", no-threshold (dashed: no confidence gate)

"recorded" bypass cells list the code paths found that never ask Jev, or "none found" in the entry-point files read; a bypass cell counts as recorded only when every entry point was read. Same terms, colours and pins as the when Jev fails map. We read source at the pinned commits; nothing was run, installed or called.

Change, 14 Oct 2026: bypass cells added for all 5 projects (previously not recorded on when Jev fails). The no-key, error, malformed and below-threshold cells above are unchanged.

Change, 19 Oct 2026: failure cells now lead with the shared map term (for example "fail-closed" instead of "fail-closed: HTTP 500"); the detail moved to the line below. No outcome changed.

A safe design, step by step

What your code should do with each Jev answer

  1. 1. Did the call fail? (no key, timeout, HTTP error)Yes: Hold the ticket for retry or a personNever map an error to a queue, archive or spam lane (D's 503 pattern)
  2. 2. Is the answer malformed? (missing key, option not in your list, probability outside [0, 1], wrong model)Yes: Treat it as an error and holdValidate as D does
  3. 3. Is the queue "other", or its confidence below your threshold?Yes: Send it to a person with the best guessAttach the probabilities, as C's internal note does; the five use 0.5–0.9
  4. OtherwiseApply the labelQueue and priority only; never a refund, cancellation or account change
Derived by the pool from the failure columns above; it is a design reading, not a measured result.

Eight rules, and which projects follow them

  1. An error is not a decision.

    On a missing key, timeout, HTTP error or malformed answer, hold the ticket for retry or a person. Never map it to a real queue, an archive lane or spam.

    DA archives
  2. Gate the queue choice on confidence.

    Below your threshold, send the ticket to a person with the best guess and probabilities. Tune the threshold on your own labelled tickets.

    BCDEA: no gate
  3. Offer an explicit "other / unclear" option and treat it as review.

    Tickets with no intent, or several, need somewhere to go.

    BDA, C, E: no "other"
  4. Validate before acting.

    The answer has the expected keys, the choice is one of your options, the probability is a finite number in [0, 1], and the model is the one you pinned.

    DA: none
  5. Set a timeout you chose.

    Or know your SDK's defaults (errors and rate limits).

    D: 20 sB, E: SDKA, C: none
  6. Send only what the decision needs.

    Subject and body, HTML stripped, length capped. Keep customer tier, IDs and contact details in your code. If a second model drafts replies, it receives the ticket too (A sends it to Groq). See what data leaves your system.

    BDE
  7. Jev answers set labels, never irreversible actions.

    None of the five refunds, cancels or changes accounts from an answer. Keep it that way.

    All five
  8. Test the routing policy offline.

    Write it as a pure function and test it without the network, including every failure branch (testing without a key).

    BDEA, C: no tests

Cost per 1,000 tickets depends on your token counts: use the cost per decision worksheet. No new prices were collected for this page.

How accurate is Jev at customer-service routing?

There is no independent ticket-accuracy test. The closest published figure is TypeSafe's own WorkflowEvals customer_service workflow (204 cases, "Customer-service routing and actions under three policies"). It scores agreement with LLM reference answers (GPT-6 Astra and Claude Fable 5.1), not accuracy against human-labelled tickets. Reported Graded as B01 on the benchmarks ledger.

  • Sol (workflow)78.3%
  • DS v4 flash76.8%
  • DS v4 pro76.1%
  • Jev (workflow)76.0%
  • Opus 572.4%
  • Sonnet 569.3%
  • Haiku 4.555.4%

TypeSafe lists Jev at $0.0001 per case and 0.4 s on this workflow. Read on evals.typesafe.ai, 1 Oct 2026, 05:35 UTC. A vendor's own test: use it as a starting point for your own labelled sample, not as ticket accuracy.

How the five were chosen

Three GitHub repository searches on 1 Oct 2026 ("jev triage", "jev ticket", "jev support": 272, 70 and 158 hits). From the results, five support-ticket projects with a real Jev call path were pinned to one commit each and read from source. No code was installed or run and no Jev call was made. Excluded: repositories that compare Jev with LLMs on synthetic tickets (for example benkohcc/jev-ticket-triage), a project using OpenJev instead of hosted Jev, and one using a local "jeff" sidecar. Several other repositories share common names such as jev-triage and were not read.

The same failure questions are asked of six moderation projects on content moderation (holding, removing and appeals) and of six model routers on model routing. Demo videos of ticket triage are listed on the videos page; the worked ticket example on What is Jev? explains a single request.

What was not verified

  • Live operation of any of the five projects: all are code-backed, none independently verified as operating.
  • The official JS SDK's default timeout (project B relies on it).
  • The remaining 70 or more triage repositories found by search.
  • Accuracy of any project's routing: no project publishes it, and the pool ran none.

Sources and check times (1 Oct 2026, UTC)

  • Projects, read at pinned commits (05:32): A (lib/jev/*.ts, lib/router.ts, app/api/triage/route.ts, lib/agent.ts); B (src/triage.ts, src/server.ts, test/decide.test.ts); C (app.rb, config/groups.yml); D (jev_core.py, app.py, webhook.py, policy.json); E (triage.py, cli.py, tickets.py, taxonomy.py).
  • Search: GitHub repository search for "jev triage", "jev ticket" and "jev support" (05:32).
  • Evidence box: evals.typesafe.ai and the WorkflowEvals README at commit 0ac3b8a (05:34).
  • SDK timeouts: Python SDK defaults as recorded on errors and rate limits.

Search published pools, pages, reports, and evidence.