PUNKthe adaptive runtime

//DOCS Enterprise Pilot

Observe-first proof-of-value sequence from first traffic through evidence review and expansion.

Enterprise Pilot

Use this path when a business wants to evaluate Punk on real agent traffic without changing production behavior on day one. The goal is to build evidence in order: observe-only traffic, first-week report, shadow pilot, canary, proof review, then expansion.

This is not a separate product surface. It is the operating sequence for using the gateway, dashboard, governance, learning, artifacts, and approvals with low initial risk.

Pilot Shape

Start with one repeated job, one owner, one app identity, and one observe-mode key.

Good first jobs:

JobWhy it works
Support triageRepeated inputs, reviewable categories, low-risk reads, clear output schema.
Vendor reviewEvidence collection, spend thresholds, approval gates, reusable scorecards.
Pricing monitorScheduled web reads, structured extraction, diffs, low write risk.
Lead enrichmentCRM and web reads first; writes can be added after approval policy is proven.
Compliance precheckEvidence burden is explicit and high-impact actions can stay human-approved.

Avoid first jobs that are mostly one-off creative writing, unbounded brainstorming, or high-impact writes. Those can still use Punk later, but they are poor starting points for proving route safety and savings.

Phase 1: Observe-Only Integration

Objective: collect trustworthy traces without changing serving behavior.

  1. Create a tenant API key in observe mode.
  2. Route one existing OpenAI- or Anthropic-compatible app through Punk.
  3. Send X-Punk-App, X-Punk-Agent, and X-Punk-Subject on every request.
  4. Keep provider keys in Punk's hosted provider configuration or tenant BYOK vault.
  5. Add SDK tool tracing only for the tools that matter to the first job.
  6. Classify side effects before any write path is considered eligible for optimize mode.

Observe mode means Punk returns live provider responses while recording the policy decision and the route it would have used. This is the right default for first production-like traffic.

Minimum evidence after the first day:

EvidenceWhere to inspect
Runs are visible with route, cost, latency, and trace events.Runs
App, agent, and subject identity are present.Run detail
Policy verdicts are understandable.Run detail and Governance audit
Repeated shapes start to group or explain abstention.Patterns and Learning
Ghost savings are visible when an optimization would have applied.Overview, run explanation, PunkBar

Phase 2: First-Week Report

Objective: turn observed traffic into a decision record.

Produce the report after enough representative traffic has run for a few business days. Do not wait for a perfect optimization story; the first report should make clear what Punk can already explain and what needs more evidence.

Include:

SectionQuestions to answer
Traffic coveredWhich apps, agents, subjects, models, and tools were observed?
Cost and latency baselineWhat did live provider traffic cost, and where were the slow paths?
Repeated workWhich patterns appeared, which did not, and why?
GovernanceWhich actions would have been allowed, blocked, or approval-required?
Side effectsWhich tools are level 0-4, and which writes remain out of scope?
Candidate optimizationsExact cache, semantic cache, tool cache, model substitution, artifact, or no action.
Evidence gapsMissing identity, unstable prompts, unclassified tools, insufficient samples, unclear output contract.
Recommended next stepStay observe-only, start shadow, add tracing, tighten policy, or stop the pilot.

Use the report to decide one narrow shadow pilot. A useful report is operational: it names the workflow, risks, evidence, owner, and decision.

Phase 3: Shadow Pilot

Objective: compare candidate optimized routes against live traffic without serving them.

Shadow only the patterns that have a stable input shape, reviewable output contract, and acceptable side-effect posture. Side effects must be suppressed during replay and shadow. User-visible and high-impact writes should stay live plus approval until their policy and rollback path are explicit.

Shadow readiness checklist:

  • The pattern represents real work, not test traffic.
  • Output correctness can be checked structurally, semantically, or by a reviewer.
  • Tool side-effect levels are declared.
  • Replay results exist for relevant history.
  • Shadow results compare against live traffic without firing duplicate side effects.
  • The workflow owner can explain fallback behavior.

Evidence to review:

EvidenceRequired interpretation
Replay pass/failDid the candidate match historical traces?
Shadow pass/failDid it match new live traffic while live remained authoritative?
Output diffAre mismatches acceptable, explainable, or blockers?
Policy verdictWould optimize mode allow the route?
Route explanationIs the decision understandable to an operator?
Rollback pathCan the candidate be quarantined or retired without app changes?

Phase 4: Canary

Objective: serve a proven route to limited traffic with explicit monitoring.

Enable canary rollout only after proof review. Keep the scope narrow:

  • One app or agent.
  • One pattern or artifact.
  • One owner.
  • One rollback decision path.
  • One monitoring window.

Canary review should watch route mix, savings, latency, policy decisions, output diffs, fallback rate, and user feedback. If confidence drops, quarantine the artifact or return the key to observe mode.

Canary does not remove the live provider path. Punk's router should fail open to live provider traffic when an optimized route is unavailable or unsafe.

Phase 5: Proof Review

Objective: make promotion a recorded decision, not an assumption.

Before expanding traffic, the owner and operator should review:

TopicDecision
PatternWhat traffic is matched, and what traffic is excluded?
Artifact or routeWhat optimized path will serve?
ReplayWhich historical traces passed or failed?
ShadowWhich live comparisons passed or failed?
Side effectsWhat was suppressed, approved, or never eligible?
PolicyWhich rules allow, block, or require approval?
SavingsWhat cost and latency reduction is measured, not projected?
RollbackWho can quarantine, retire, or switch back to observe?

Promotion is ready when the decision can be explained from dashboard evidence and reproduced from the trace ledger. If the evidence is weak, keep the route in shadow or observe mode.

Phase 6: Expansion

Objective: add coverage without making the system harder to reason about.

Expand in this order:

  1. More traffic for the same app and pattern.
  2. More subjects for the same workflow.
  3. More read-only tools with declared side-effect levels.
  4. Reversible writes with idempotency and approval posture.
  5. Additional apps that share the same governance model.
  6. Higher-impact writes only after approval, audit, and rollback are exercised.

Each expansion should have its own observed baseline, evidence review, canary, and rollback path. Avoid mixing pilot test traffic with production-like traffic when judging pattern confidence.

Developer Checklist

  • Use the base URL swap first.
  • Keep the application request shape stable.
  • Send identity headers on every request.
  • Store provider keys in Punk, not in application code.
  • Add SDK tracing for important tools after model traffic is visible.
  • Declare side-effect levels for tools.
  • Keep write paths observable before making them optimizable.
  • Use feedback when a response is wrong or notably correct.

Operator Checklist

  • Issue separate observe and optimize keys.
  • Scope keys to apps where possible.
  • Review provider key source and credential storage.
  • Decide retention and redaction before broad traffic.
  • Write policy for the first app and agent.
  • Require approval for level 3 and 4 actions during the pilot.
  • Review audit events daily during the first week.
  • Enable canary only after proof review.

Progressive Disclosure

Do not make every advanced feature part of day-one onboarding. Expose features in the order the pilot needs them:

StageShow firstDefer until needed
Observe-onlyRuns, route explanations, cost, latency, identity, policy verdicts.Artifacts, model substitutions, connector catalog depth, advanced settings.
First-week reportPatterns, learning notes, side effects, ghost savings, evidence gaps.Manual artifact controls, cross-tenant learning, custom policy tuning.
ShadowReplay, shadow comparison, output diffs, suppressed side effects.Full workflow editing, global optimization knobs.
CanaryRoute mix, fallback, confidence, rollback, approval state.Broad automation, high-impact writes, automatic promotion.
ExpansionApp-level coverage, owner cadence, policy reuse, audit exports.Organization-wide optimization defaults.

Progressive disclosure should hide complexity from first-time users without removing capability. Advanced controls remain available to operators and developers when the evidence says they are relevant.

Definition Of Done

The enterprise pilot has a credible starting point when:

  • One real app is routed through Punk in observe mode.
  • Representative traffic appears in Runs with complete identity.
  • The first-week report names baseline cost, latency, repeated patterns, policy posture, side effects, and evidence gaps.
  • One candidate route has replay and shadow evidence or a clear reason it is not eligible.
  • Canary criteria and rollback are documented before optimize mode serves production-like traffic.
  • The expansion plan adds one risk dimension at a time.