Aidan Tiruvan
Founder of Archal, API sandboxes, built for AI agents
Company
Aidan Tiruvan is listed as a founder of Archal. Archal provisions sandboxes with the API environments your CI, tests, and evals need. Your coding agent can start the sandbox & environments, connect to your API integrations, run tests, and inspect state changes. Sandboxes and environments are startable within seconds and take milliseconds to reset.
Founder traction evidence
Public posts and activity attributed directly to this founder.
- X
Just launched Archal (YC S26): API sandboxes built for AI agents! Your coding agent can spin up Slack, Linear, Datadog, and 20+ stateful environments for CI and evals.
Just launched Archal (YC S26): API sandboxes built for AI agents! Your coding agent can spin up Slack, Linear, Datadog, and 20+ stateful environments for CI and evals. It can run tests, inspect state changes, and reset everything. Ask your agents about https://t.co/XJK3cufSKh
- LinkedIn
They ain't believe in us... GOD DID 🗣️🗣️ ‼️ Excited to announce that Archal is backed by Y Combinator! Noah and I used to laugh at headlines of AI agents breaking production databases. Now we're… | Aidan Tiruvan | 45 comments
GOD DID 🗣️🗣️ ‼️ Excited to announce that Archal is backed by Y Combinator! Noah and I used to laugh at headlines of AI agents breaking production databases.
- LinkedIn
We're excited to introduce Archal publicly, the first deterministic eval platform for AI agents. Software testing exists because we figured out that catching bugs before users do is cheaper than catching them after. Somewhere in the last two years that lesson got lost. Agents ship without anything resembling a test suite or with simple mocks and Langfuse strapped on. Observability tools only tell you about these bugs after a customer is already affected. We built Archal because there's no excuse for this in the big 26. …more
We're excited to introduce Archal publicly, the first deterministic eval platform for AI agents. Software testing exists because we figured out that catching bugs before users do is cheaper than catching them after. Somewhere in the last two years that lesson got lost. Agents...
- X
When building an agent, it always bothered me that I could not evaluate exactly what actions it could take before dropping it into production. At Scale AI, we've always pushed the notion that evals are intuitively the best way to see how an LLM performs. When coupled with a Show more Quote Archal @archal_labs · May 26 Today we're excited to introduce Archal publicly, the first deterministic eval platform for AI agents. Software testing exists because we figured out that catching bugs before users do is cheaper than catching them after. Somewhere in the last two years that lesson got lost. 0:01 / 1:11
When building an agent, it always bothered me that I could not evaluate exactly what actions it could take before dropping it into production. At Scale AI, we've always pushed the notion that evals are intuitively the best way to see how an LLM performs. When coupled with a...
- X
this is super impressive; reminds me of agent trajectories but for robotics data
this is super impressive; reminds me of agent trajectories but for robotics data
- X
a wise man once said: "slow motion is better than no motion" I made that shit up but thought it could be applicable to initial startup growth
a wise man once said: "slow motion is better than no motion" I made that shit up but thought it could be applicable to initial startup growth