Production AI agents, eval-gated before they ship.
We design an agent around one real job, wire it direct to the model with no framework lock-in, prove it against an eval suite you keep, and hand it over running in production.
Who it's for: Teams past the demo stage who need an agent that behaves the same on the thousandth run as the first, with an owner and a rollback path.
- Outcome
- Agent in productionnot hours billed
- Engagement
- Fixed scope
- Timeline
- 8 weeks
- Investment
- from $28,000+ optional care retainer
- Handoff
- Full source + ownership
What the engagement covers.
- ✓One agent scoped to a single, measurable job
- ✓Direct model integration, no orchestration framework
- ✓An eval suite of 50 to 200 labeled cases with a ship gate
- ✓Observability: latency, cost, and quality per route
- ✓Up to 2 system integrations against your tools
- ✓A runbook and one paired handoff week
What we would quote separately.
- –A net-new data platform or warehouse build
- –Unlimited integrations beyond the two included
- –24/7 staffed on-call operations
- –A net-new mobile or web front-end product
- –Ongoing content or prompt authoring after handoff
What lands at handoff.
- ✓The agent, deployed and running in production
- ✓The eval suite, and the bar it must clear to ship
- ✓An observability dashboard for cost, latency, and quality
- ✓A runbook: how to operate, extend, and roll back
- ✓Full source code with complete ownership
- ✓One paired week where your team ships a change
8 weeks, problem to production.
- 01Weeks 1 to 2
Scope and evals
Pin the one job, write the eval set and the ship gate before any model code.
- 02Weeks 3 to 5
Build
Direct-to-model agent on a typed, tested base, with observability from the first commit.
- 03Weeks 6 to 7
Harden and test
Close the failure modes the eval set surfaces, and red-team the prompt boundary.
- 04Week 8
Ship and hand off
Deploy with monitoring, a runbook, and a paired week so your team owns it.
The SLA this service runs under.
During the build and through the warranty window after handoff. This engagement defaults to Priority.
| Commitment | Standard | Priority |
|---|---|---|
| First response | Next business day | Within 4 business hours |
| Critical issue triage | 1 business day | 2 hours |
| Production uptime target | 99.5% | 99.9% |
| Support hours | Mon to Fri, business hours | Extended, plus weekend on-call |
| Change requests / month | 2 included | Unlimited within retainer |
| Post-launch warranty | 30 days | 90 days |
| Named delivery lead | Shared | Dedicated |
ⓘStandard ships with every fixed-scope build. Priority comes with a care retainer. Pricing is a starting range; final terms are set in the statement of work.
Read the full AI Agents capability page ↗