Turn real-world behaviour and expert decisions into controlled improvement loops, so AI keeps learning without drifting beyond the boundaries you set.
30 minutes with the founder. Bring one live AI failure; leave with an improvement plan.
Improving AI for teams deploying in:
Four steps, one surface. The traffic that arrives at the gateway is the same traffic you evaluate, improve and hand to an agent.
Send calls through the Python SDK, or point your OpenAI client at the gateway, and every call is captured as a trace: request, response, latency and route. Tag each call with its use case, then filter by tag, model or status to see exactly what your product is doing.
Pick a tag and a date range, choose whether to test the prompt or the model, and Stimulir scores it on that real traffic in the background. Traces are cleaned before scoring, and you can save the selection as a dataset to run again.
Every evaluation ends in a report: your current prompt’s score, the new prompt’s score and the difference, with the cases that changed most. Copy the new prompt into your code, or apply it in Stimulir. A model evaluation tells you which model to use.
Hand a task to the Stimulir agent, or to your own coding agent through the CLI. It reads your traces, runs the evaluation and proposes the fix, with a person approving before anything ships.
npx stimulir setup
Mission
Walkthroughs that play step by step in the docs for the quickstart, API keys, datasets and the first evaluation. Watch it before you do it.
Pro tokens cover the listed models, so a team sends its first real request without adding a provider key.
An empty thread now opens with three starter cards: send your first real request, check whether a cheaper model holds up, run the demo.
Every failure on the real traffic path now says what happened and what to do next, with the code kept for support.
Pricing
One workspace to build, trace, evaluate and approve. Start with 7 days of Pro, then choose what fits.
Regularly $100/month. Keep $50/month for your first 12 paid months, then $100/month.
From a first visual agent to a better production workflow, with evidence behind every change.
No card required. After the trial, keep 20 free traces per month unless you upgrade.
Included with paid Pro. Additional usage billed separately.
Try Pro for 7 days with no card required: build an agent or connect an existing workflow, inspect traces, evaluate a change and approve the better version. A small starter allowance covers managed-model usage.
Customer-controlled compute peers during the trial are available by arrangement. The $25 monthly managed-model credit starts with paid Pro. If you do not upgrade, continue on Free with 20 traces per month.
Your subscription covers the workspace, builder and improvement tools within your plan’s limits. Paid Pro includes $25 in managed-model credit each month; additional managed-model usage is billed separately.
With your own provider keys, you pay your provider directly with no Stimulir model markup. Your own compute carries no Stimulir GPU charge; normal platform limits still apply. If Stimulir provisions rented compute for you, provider costs and any orchestration margin are disclosed separately.
The first 10 paying teams keep Pro at $50 per workspace per month for their first 12 paid months. After that, Pro is $100 per workspace per month. The free trial does not start your 12 paid months.
All prices in USD, excluding applicable taxes.
Pro for 7 days, no card and no provider key. Keep 20 free traces per month after your trial.
30 minutes with the founder. Bring one live AI failure; leave with an improvement plan.