Know what your
AI work
actually did.

Track scheduled LLMLLMA large language model is a text-focused AI model trained on large amounts of data to understand, generate, summarize, translate, or reason over language.View glossary entrySource: Google Cloud Generative AI glossary batchesbatchA group of records or tasks processed together. Batch jobs are often monitored by counting processed items, failed items, duration, and cost.View glossary entrySource: Anthropic API overview, random agentagentAn AI application that uses a model, instructions, state, and tools to work toward a goal. Agents are useful to monitor because they can run for a while and make multiple tool calls.View glossary entrySource: Google Cloud Generative AI glossary workersworkerA background process that performs work outside the main request path, such as syncing data, generating reports, or running AI tasks.View glossary entrySource: GitHub Actions CI docs, RAG syncsRAGRetrieval-augmented generation improves model output by retrieving relevant information from a knowledge source and grounding the response in that context.View glossary entrySource: Google Cloud Generative AI glossary, eval runsevalA test or scoring run used to judge whether an AI system behaved well enough. TelemHQ can track eval score, pass rate, failures, and regressions.View glossary entrySource: Google Cloud Generative AI glossary, and AI reports with heartbeatheartbeatA lightweight signal that proves a job checked in. TelemHQ extends heartbeats with payload data so the run can explain what happened.View glossary entrySource: TelemHQ docs pingspingA request sent to TelemHQ after a job runs. A ping can be a simple heartbeat or include JSON payload data about what happened.View glossary entrySource: TelemHQ docs plus structured payloadpayloadThe structured data sent with a request. In TelemHQ, payloads should contain safe operational metadata, not prompts, completions, secrets, customer data, or private paths.View glossary entrySource: MDN API glossary data. Use it solo, or invite teammates so managers can see project-level tokenstokensThe pieces of text an AI model processes. Token counts are often used to measure usage and calculate model cost.View glossary entrySource: OpenAI token guide, spendcostThe money associated with a run, often estimated from token usage and provider pricing. TelemHQ can store cost fields when your job sends them.View glossary entrySource: OpenAI token guide, failures, and per-user activity in one place.