Analysts who start every case from an organised picture.

The client

The client is an organisation that works with security bodies and research. Its team builds case files on people and organisations. The analysts are experienced, and their job is to connect details scattered across many places.

The challenge

Every case started from scratch. The analyst searched different sources, cross-checked them and linked the entities by hand. Most of the time went on gathering, and less on what really takes expertise: judgement.

What we built

• 1. An entity and relationship graphEvery person, organisation and piece of information in a case goes into one graph, so the connections are visible at a glance.
• 2. A research agentFor each case the agent runs automated research in open sources and adds what it finds to the graph.
• 3. The analyst decidesThe agent gathers and organises, the analyst checks and decides. Judgement stays with the person.

The result

Instead of building every case by hand, analysts start from an organised picture the agent has already gathered. Their time moves from gathering to judgement.

Why it worked

We didn't try to replace the analyst. We took the most draining part of the work, the gathering, gave it to the agent, and left the judgement with the people who know how to judge.

Related

• Autonomous agentsAn AI agent doesn't just answer questions. It carries out a task end to end: it reads, decides by rules we define together, acts in your systems and reports back. In a project Shahar Peer led before founding Pele, at a medical equipment company, one agent built into the existing lead process lifted lead conversion by 56%.
• Internal assistantsThe answer already exists somewhere: in a procedure, a spec sheet, a customer file or a veteran's head. An internal assistant connects that knowledge to your teams, answers in plain language and shows where the answer came from.