When Everyone Has AI Agents, Who Knows What They’re Doing?
We started building OliverGraph to give teams and their AI agents shared context across GitHub, Slack, docs, and the other places where work happens. At first, we thought the main problem was retrieval. Company knowledge is scattered across GitHub, Slack, docs, tickets, and people so we could connect those systems and get the right context to the agent when needed. But we ran into another…
OliverGraph aims to provide teams with a consolidated view of AI agents' context across various workspaces like GitHub, Slack, docs, and tickets. Initially, the focus was on retrieval, but an additional challenge arose – agents began to retain crucial context during their runs. Engineers may instruct agents about past attempts, customer expectations, or project constraints, which can vanish when the agent session concludes.
This issue intensifies during outages when multiple engineers and their respective agents investigate simultaneously, leading to duplicated efforts and confusion. As more teams adopt AI agents, understanding the broader context becomes increasingly challenging. OliverGraph intends to preserve agent run histories and link them to company artifacts such as pull requests, documentation, incidents, and personnel involved.
By doing so, subsequent agents can leverage this historical context, preventing redundant investigations and promoting efficient collaboration. The platform seeks teams interested in testing its capabilities, inviting interested parties to reach out at olivergraph.com.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
