A goal broken into ordered, tool-assigned steps with a resolved, acyclic dependency graph, so an agent (or a team) can execute it without ambiguity.
You receive: A structured plan (JSON: steps with id, prompt, parameters, assigned tool, dependencies) that passes the completeness + acyclic-graph checks.
What's verified: STUD verifies the submitted plan (JSON) is structurally complete and executable on paper: every step has a unique id, a prompt, a parameters object, and a tool assigned from your allowed tools, every dependency resolves to a real step with no self-reference, the dependency graph is acyclic, no step is orphaned, and the step count is within your max. STUD does NOT judge whether the steps are the right way to reach the goal or whether an agent could actually carry them out.
Opens soon
Cost25 credits
ProtectionHeld until verified delivery
This play is verified and ready. It opens soon, once sign-in and payments are live.
Example
A sample of what this play produces. Your result is generated for your inputs.
Steps
Ids1
PromptDefine what counts as a stale frozen param for this workspace: a frozen intake value whose current live fact (by factKey) no longer matches it. Write the freshness-check acceptance criteria.
Parameters
Workspace slugstud-dogfood
Scopefacts_freshness_definition
Assigned tollm
Ids2
PromptQuery every run's frozen intake params for the workspace, keeping only params that carry a factKey binding.
Parameters
Queryselect run_id, params from runs where workspace_id = :workspace_id
Workspace slugstud-dogfood
Assigned tosql_query
Dependencies
s1
Ids3
PromptQuery the current live workspace facts table for the same workspace, keyed by factKey.
Parameters
Queryselect fact_key, value, updated_at from workspace_facts where workspace_id = :workspace_id
Workspace slugstud-dogfood
Assigned tosql_query
Dependencies
s1
Ids4
PromptFor each frozen param from s2, look up the matching factKey from s3 and mark it stale if the frozen value no longer equals the current live value.
Parameters
Join keyfact_key
Outputstale_param_rows
Assigned topython_exec
Dependencies
s2
s3
Ids5
PromptAggregate stale_param_rows into a per-run stale count and a workspace-level staleness rate (stale rows divided by total bound rows).
Parameters
Inputstale_param_rows
Outputstaleness_summary
Assigned topython_exec
Dependencies
s4
Ids6
PromptDraft a plain-language summary of staleness_summary for the workspace owner: what changed, which runs are affected, and what to review first. Plain, factual register; no em dashes.
Parameters
Inputstaleness_summary
Voicebrand.voice_rules
Assigned tollm
Dependencies
s5
Ids7
PromptRender the plain-language summary from s6 together with the staleness_summary table from s5 into a single HTML report.
Parameters
Templatefacts_freshness_report
Inputs
staleness_summary
owner_summary
Assigned topython_exec
Dependencies
s5
s6
Ids8
PromptSend the rendered HTML freshness report to the workspace owner's registered email address.