Skip to content

Tier2How it works

From a support signal to cited evidence

Five stages, in order, with the boundary between model judgement and code enforcement drawn explicitly at each one.

Model picks the testCode evaluates the ruleRenderer enforces citations

Stage 01 · Intake

A signal arrives, untrusted

A ticket, a Slack thread, an email, or a widget message lands in the tenant inbox. A small, fast model classifies it and extracts the claim under test.

  • Ticket content is input, never instruction. The runbook is the only privileged channel into the agent.
  • Anything the agent learns from a ticket body is written to a quarantine directory with provenance, and needs a human to promote it.
  • A fact sourced from a stranger never outranks an annotation from your engineer.

Why quarantine matters

An agent that writes its own memory is one prompt-injection away from learning something false and repeating it with confidence. Separating proposed memory from promoted memory is the only defence that survives a hostile ticket.

Stage 02 · Answer, or differential diagnosis

Knowledge base first. Code decides when that's not enough.

Most tickets, for most products, are answerable from a knowledge base article — the agent checks yours first and cites the article if it settles the question. When the question is actually about your systems, each runbook is versioned YAML describing differential tests and their branch predicates; the agent chooses which test is worth running, and the predicate runs in TypeScript against the probe result.

  • A knowledge base hit ends the investigation right there — no probe needed, no guessing either.
  • Probes, when they run, are GET or handshake only, against validated public DNS names — never an IP, never a .internal host.
  • Database reads are named queries on a read replica with a statement timeout and no parallel workers.

Stage 03 · Verification

Five verdicts, two destinations

An adversarial pass reviews the diagnosis before anything is rendered — a separate step, because an agent asked to check its own work over-verifies and still misses the same things.

VerdictRouteWhat the customer gets
Already fixedDraftThe behaviour changed in a deploy after the ticket was filed. The reply names the deploy and the probe that confirms current behaviour.
Not reproducibleDraftProbes cannot reproduce the report from outside. The reply says what was checked and asks for the one detail that would change the answer.
Environment-specificDraftThe failure is in the caller’s environment — DNS, TLS, a proxy, a client version. The reply shows the probe that succeeded from ours.
Needs infoDraftThe differential cannot be narrowed without one specific fact. The reply asks for exactly that, not a generic questionnaire.
ReproducedEscalateA defect confirmed by probe evidence. This is the only verdict that reaches an engineer, and it arrives as a packet with the trail attached.

Stage 04 · Delivery

Customer replies wait. Engineering pages do not.

The draft gate exists to protect your customers, not to slow your engineers down. A customer-facing reply always waits for a human; an internal escalation posts itself.

draft reply · T-48291awaiting approval

Thanks for flagging this — we reproduced it. The slowdown started at 14:02 UTC with our v419 deploy, which reduced the connection pool from 64 to 16. Saturation reached 94% within twenty minutes. A fix is rolling out; no action is needed on your side.

deploy.diff · pr_9f2ac2replica.query · pr_9f2ac3
Approve & send EditAuto-send off
escalation packetdedup: pool_max/v419reproduced
Severity
P1 · customer-facing latency
Root cause
pool_max 64 → 16 in v419
Owner
#platform-oncall · @data-infra
Evidence
3 probes · 3 citations · 0 uncited claims
Posted without waiting for approval — internal route

Stage 05 · Correction

Being wrong is an input, not a failure

When an engineer corrects a diagnosis in the thread, that correction is proposed as a runbook diff and reviewed the way a pull request is. Nothing takes effect until it has been scored against the labelled eval set.

  1. Correction

    An engineer replies in the thread

    “The pool size is not the cause — the control-plane field is stale, check the replica.”

  2. Proposal

    The runbook change is drafted as a diff

    The field trust map marks the control-plane column stale, and the test order changes so the replica read runs first.

  3. Gate

    The replay harness scores it

    The change is replayed against every labelled escalation. A runbook edit that cannot be scored does not merge.

  4. Effect

    Next month’s ticket is answered by it

    Diagnosis quality compounds with your team’s attention instead of decaying with your documentation.

Ready when you are

Replay one of your escalations.

Pick a ticket your team already resolved. We show you the probes it would have fired and what it would have drafted.

Draft-only by defaultRead + probe access only