Introduction

Agents are powerful AI workers built into HASH, which answer questions, work towards goals, and execute flows on your behalf.

To view or manage your agents, click on the "Agents" tab in the left-hand sidebar of the HASH app. From here you'll be able to view their activity, provide them with new goals, or chat with them to get answers directly.

Supporting goals

Agents can help solve goals on your behalf. Currently, agents support research and analysis related tasks — for example, adding new entities to, or enriching existing entities within — your web, by autonomously researching topics and analyzing the collected information.

When conducting research, agents are able to search for and interpret information already in your web, as well as public entities from other HASH webs, and the outside World Wide Web. As always, private information within both personal and shared webs is not accessible to anybody else (including other people's agents).

Answering questions

Agents can also help you understand topics with more expertise and in more detail than ordinary AI chatbots, by combining their own knowledge and access to the World Wide Web, with information from HASH (including data in your own personal web). Answers are supplemented with references to the entity, webpage, or other context used in their production, so you can have more confidence in the underlying reasoning.

Managing flows

Flows are pre-defined series of steps that Agents can execute. If something goes wrong, depending on how the flow has been set up and defined, the agent executing it has the ability to decide how to proceed.

Ensuring data accuracy

HASH is a self-checking knowledge graph, and agents play a central role in keeping the information in your web accurate and up to date. They can re-check existing entities against their original sources, flag conflicting or outdated information, and record the provenance of every claim — so you can always see where a piece of information came from, and how much to trust it.

Where an agent isn't sure how to resolve a discrepancy, it will ask you to confirm, surfacing the question in your inbox rather than guessing.

Maintaining your ontology

Agents also help keep your types in good shape. As they add information to your web, they map data to existing entity types and property types wherever possible, and — where appropriate — propose new types, or extend existing ones, so that your ontology grows in a consistent, well-structured way rather than becoming fragmented over time. Helpfully, they can help reconcile user-suggested changes into a structure that remains consistent org-wide.