Skip to main content

Glossary

One-line-per-term summary across the whole wiki. The lexicon, flattened.

Every coined term on one line, linked to its canonical page in Concepts.

  • Agent Once, Session Every Run: create the versioned agent config once, create a session per run; agent creation in the request path is the anti-pattern.
  • The Audit Trail: citation to source as a product feature, so the human verifies instead of hunts.
  • The Batch API: 50 percent off input and output tokens for anything that can wait up to 24 hours; stacks with caching.
  • The Company Brain: a persistent store of how a specific company works, which agents read on every run and write back to as they learn.
  • Consumption Pricing: the platform bills by tokens consumed, not seats sold, so the bill scales with how much the product actually runs.
  • The Deployment: everything an agent runs on: sandboxing, session persistence, tenant isolation, secrets handling, and capacity.
  • The Effort Dial and Model Splitting: frontier-model tokens for judgment, small-model tokens for commodity steps, effort turned down where thinking is wasted.
  • The Four Ways to Build: manual loop, Tool Runner, Agent SDK, Managed Agents, separated by who supplies the harness and who supplies the deployment.
  • The Harness: the software loop around the model: tool dispatch, context management, retries, and compaction.
  • The Human Gate: an approval step the platform enforces before an action commits; a prompt asks, a permission policy guarantees.
  • Long-Running Work: agent runs measured in hours rather than seconds: the workload class that makes every architecture decision matter.
  • Memory Stores: workspace-scoped persistent memory mounted into every session, versioned and auditable.
  • The No-API Integration: operating the screens of systems that will never get an API.
  • Outcomes: define done as a rubric, and the platform runs an iterate, grade, revise loop with a separate grader until the work passes.
  • Prompt Caching: cached input reads cost a fraction of base price, but one changed byte in the prefix invalidates everything after it.
  • Scheduled Deployments: cron for agents: a schedule fires a fresh session on the clock, and every firing leaves a run record.
  • Self-Correction Mid-Task: an agent that checks its work against reality before handing it over, and fixes what it finds.
  • Silent Failure: the failure mode that kills trust in unattended agents: the agent thinks it finished, and it did not.
  • Vaults: secrets never enter the sandbox; they are substituted into outbound requests at egress.