Continuous eval gates in CI/CD
Block merges when agent prompts/tools regress — hosted eval suites, datasets, and pass/fail gates wired to GitHub/GitLab CI.
At a glance — Oct 2026
Updated 2026-10-27 · forward this page: /jtbds/continuous-eval-ci#briefScores as of 2026-10-19 (8 days old).
- Depot Pick
- Braintrust · 8.34/10 for this job (curated estimate, high confidence)
Distinct from `evals` (general harness): CI gate DX + dataset versioning + flake control. Confidence: high for Braintrust/Promptfoo CI docs.
- Runner-up
- Promptfoo · 8.46/10
Scores higher than the pick on: Price / performance, Privacy / data retention, Lock-in risk (higher = worse).
- When not to use the pick
- Want OSS-first local gates (Promptfoo), DeepEval/Confident already standardized, or LangSmith is the org tracing system of record.
- Lock-in / migration
- Runner-up Promptfoo has lower stored lock-in risk (2.5 vs 5, 0–10, higher = more lock-in). Self-host fallback listed for this job: Promptfoo.
- Sourced price (no comparable unit)
Pick: no sourced price in this job's unit (no_sourced_price).
No cheapest SKU (no_comparable_unit_for_job). No price was invented.
- Free option
- Promptfoo (oss) — source, as of 2026-10-25
- Failure modes to watch
- Benchmark protocol mismatch: Store assisted-or-not, subset, and harness version beside every cited score. Refuse a ranking that mixes those fields.
- Eval contamination: Keep gold labels out of the agent prompt. Store the harness version beside the score. Do not compare a number across a benchmark revision without saying the revision changed.
- Inter-agent misalignment: Log the assigned subtask next to the worker's stated result. The lead rejects a result that does not match the assignment.
- Non-determinism: Run the task more than once and compare the end state, not a single transcript. Record the trial count next to any success rate you cite.
- Observability gap: Alert on a drop in trace ingestion and on certificate expiry for the trace host. Do not treat a missing trace as a successful quiet run.
- Weak verification: Success requires an end-state check the agent does not grade for itself: tests, a database diff, or a separate judge that cannot see the gold label.
Cite: Agent Provider Depot, Depot Pick for continuous-eval-ci: braintrust, scores as of 2026-10-19. Agents: GET /api/decide?jtbd=continuous-eval-ci
Free Eval CI gates options · for eval-judge agents
Braintrust
Distinct from `evals` (general harness): CI gate DX + dataset versioning + flake control. Confidence: high for Braintrust/Promptfoo CI docs.
Pricing (directional): Eval-first platform; data-based pricing with unlimited seats on many plans; strong CI eval story.
Lock-in risk: higher = more lock-in (worse). Overall already inverts this dimension.
Depot pick when evals are the product quality gate. Pair with Helicone/Langfuse for cheap request logs if needed.
Quote for Continuous eval gates in CI/CD
Depot Pick stays Braintrust. Prices below are sourced SKU rows only (as of 2026-10-27). Input and output are not blended. GET /api/quote?jtbd=continuous-eval-ci
Nothing was compared. no comparable sourced unit for this job; chat input $/1M and other units were not borrowed pickIsPriceWinner is null.
Sourced price unavailable for the Depot Pick. No row in the pricing index.
5 of 5 candidates have no sourced price row. 5 are excluded from the Matching price comparison (none). no comparable sourced unit for this job; chat input $/1M and other units were not borrowed
Runners-up
Promptfoo
Default OSS eval harness. Braintrust when you want hosted collaboration; Promptfoo when you want local/CI…
Confident AI
Best when your team already thinks in pytest/DeepEval. Braintrust remains Depot hosted-evals default…
LangSmith
If you live in LangGraph, LangSmith is the obvious observatory. Otherwise compare Langfuse/Helicone first.
Patronus AI
Layer on when regulated hallucination/safety gates matter more than general CI evals. Lakera for injection…
When NOT to use the top pick
Want OSS-first local gates (Promptfoo), DeepEval/Confident already standardized, or LangSmith is the org tracing system of record.
Full ranking (score table)
Ranked with this JTBD's weights. Scores are curated estimates unless marked otherwise. Agents: prefer /api/decide then this table for tie-breaks.
| # | Provider | Overall | Fit | $/perf | Latency | DX | As of |
|---|---|---|---|---|---|---|---|
| 1 | Promptfoo | 8.5 | 8.2 | 9.2 | 7.8 | 8.8 | 2026-10-19 |
| 2 | BraintrustDepot Pick | 8.3 | 9.2 | 7.5 | 8.6 | 8.8 | 2026-10-19 |
| 3 | LangSmith | 8.3 | 9.0 | 7.0 | 8.8 | 9.0 | 2026-09-14 |
| 4 | Confident AI | 8.2 | 8.6 | 7.8 | 8.0 | 9.0 | 2026-09-14 |
| 5 | Patronus AI | 7.3 | 8.4 | 5.5 | 8.0 | 7.2 | 2026-09-14 |
Score methodology for this job
Distinct from `evals` (general harness): CI gate DX + dataset versioning + flake control. Confidence: high for Braintrust/Promptfoo CI docs.
capabilityFit: 22%pricePerformance: 14%latencyReliability: 14%developerDx: 28%privacyPosture: 8%lockInRisk: 6%maturity: 8%