Set an agent loose to plan, call tools, and do the work — with hard limits on how many steps it takes, how long it runs, and when to stop, all enforced by Catalyst rather than left to the model's good intentions. Every step is visible. You can pause, step in, or stop it instantly at any point.
The agent keeps going until the model stops reaching for tools — bounded by hard limits Catalyst enforces, not by the model's self‑restraint. Three dials, every run.
How many rounds of planning and tool‑calling the agent can run. Most real tasks finish in three to seven; the hard ceiling of 50 means even a worst case can't run away.
Total real‑world time the run is allowed. A slow tool call still counts against it. When time's up, the agent stops where it is and you get whatever it finished so far.
Give it a word or phrase to watch for; the moment the model's answer contains it, the run ends — even if it had rounds to spare. Handy for "stop as soon as you have the answer."
Agents are usually black boxes — input goes in, output comes out, the middle is a guess. Not here. Catalyst shows every step as its own card: which tool the model reached for, what it sent, what came back, how long it took, and whether it failed. Click any card to open the full details.
Agents come with three starting patterns proven in production. Start from one and mix in your connected tools as you go.
Take a question, search the web and your own docs, read the sources, and pull it together. Capped so it doesn't dig forever.
Take a dataset — a spreadsheet, a file, a query result — run Python in a private sandbox with pandas / matplotlib, and return a chart plus a written summary. It keeps going until the answer holds up to its own checks.
Pull live market data, crunch the numbers in Python, format the result, and email it out. The go‑to setup for "every weekday morning" scheduled agents.
Agents earn trust through transparency, not promises. Caps the model can't bypass. Transcripts you can audit. A stop button that actually stops.