plannedShip
Board Deck Analyst
Ask a plain question of last quarter's numbers; get the chart, the query it ran, and a one-page memo, in one minute.
Ask us to build this firstService
AI product engineering
Products with AI inside: planners, writers, analysts and assistants that pass an eval bar and stay inside a cost ceiling.
4 things we build · 3 offers on this path · 3 demos
01Multi-agent systems on Google ADK or the Claude Agent SDK
02Structured outputs, tool use and tracing from day one
03Golden test sets run in CI before launch and every week after
04A cost gateway with per-feature budgets
Offers on this path
Where to start.
Fixed price after paid discovery, never on a meter. Every offer has a scope, a duration and a risk reversal.
Shape Pilot4 to 8 weeks
One use case on real data in your tenant, with golden-set evals, guardrails, tracing, a cost dashboard and handover
₹6 to 20 L · $15k to 45k
Acceptance is a pre-agreed eval bar plus a cost ceiling. If missed, up to two weeks' extension free. You own the repo from day one.
Ship Build8 to 16 weeks
Production build, integrations, security review, monitoring, runbook, training, 30-day hypercare
₹20 to 60 L · $45k to 150k
Milestone-fixed fees.
Ship Retainermonthly, 3 minimum
A senior agentic engineer embedded three to four days a week, building and transferring
₹4 to 10 L / month · $8k to 22k / month
30-day exit after month three.
Related demos
What this looks like running.
Planned, not live. Each one shows its eval score, its cost meter and its trace when it runs.
liveSustain
Agent Autopsy
Six real ways agents fail in production (loops, cost blow-ups, tool misuse, stale retrieval, prompt injection, silent regressions), replayed from traces, with the fix for each.
Ask us to build this firstplannedScale
Gateway Meter
Send one prompt to three models through our cost gateway and watch price, latency, cache hits and the budget cap behave in real time.
Ask us to build this first