// verdict · checked 2026-08-11 · Lindy 3.0 agents (docs.lindy.ai, 2026)
Lindy
Lindy
Email triage that mostly triages. Closest thing to an agent your inbox has met.
- CAPABILITY
- 4/5 AGENT
- PROOF
- OPERATOR INSPECTABLEYou can run it and read the steps yourself — the record exists for whoever runs it
- TRACE ACCESS
- OPERATOR-OWNEDWhoever runs it holds the record; nothing is published
- LEASH
- Not measuredno execution record scored — measure it yourself
| LOOPSruns until doneyes | Agent step runs its own act-then-check loop: docs say it keeps working until an exit condition is satisfied, evaluating after each action, so step count varies by task. |
| CHOOSESpicks its own toolsyes | Docs: "Instead of following fixed workflows, they work from guidelines you provide and choose which skills to use based on the situation"; skills repeat and reorder mid-run. |
| ACTSchanges the worldyes | Integration actions write to external systems (send email, update records, create calendar events) and the Use Computer skill drives a real browser session to click and submit forms. |
| RECOVERSfixes its own errorsno | Errors stop the task and email you; docs say recovery is a human clicking Retry — not automatic. |
| UNSUPERVISEDnobody watchingyes | "Ask for Confirmation" is an opt-in per-action toggle you enable, so with it off a schedule or event trigger runs the whole task end-to-end with nobody present. |
Capability decisions combine documented behaviour and execution evidence. The proof label on each row shows which of the two decided it, and Leash is reported separately, only when it was measured from an execution record. Primary source: docs.lindy.ai. Tested against: Lindy 3.0 agents (docs.lindy.ai, 2026). Our confidence in this dossier: 7/10.
Can you see it work?
the weakest of the five grades aboveOPERATOR INSPECTABLE — You can run it and read the steps yourself — the record exists for whoever runs it. Trace access: OPERATOR-OWNED — Whoever runs it holds the record; nothing is published.
Tasks view opens any run step-by-step; Get Task Details returns block-by-block I/O
Where we looked: docs.lindy.ai raw .md for /testing/monitoring-your-agents, /testing/debugging, /skills/lindy-utilities/observability; llms.txt index; web search · see the evidence → · re-checked by a second pass built to overturn it
No revisions yet. This verdict has stood since 2026-08-11.
Badges
earned, never for sale
These render from the live dataset, so a badge cannot outlive the verdict it claims. If the verdict changes the badge changes with it, and an unearned one returns 409 rather than an image. No sponsor can buy one, at any price.
Think this is wrong?
bring evidence, not opinionName the criterion and link a trace, a doc, or a recorded run that shows the behaviour. A verdict changed by evidence is the best thing that can happen to this site, and the change goes on the public record with your reason attached. Vendors are welcome, and a vendor's own filing is labelled as such rather than buried.