DeepVista
It's Time for Relational Intelligence
Nov 20, 2026 · @Jing Conan Wang
AI can reason about the world. But it often lacks the relationship history needed to act in it.
What we can do in the world depends in part on our relationships with other people.
A former colleague who has seen your work can vouch for it from experience. Someone you met once may know what you do and have little basis for recommending you. The history between you shapes what each person can credibly say and do on your behalf.
We call this relational context. It’s how people know each other, what they’ve done together, and how those relationships change over time. It lives in careers (where people worked, when, and alongside whom) as well as in the meetings, emails, and projects they share.
As AI agents help us make more decisions in the real world, they’ll need access to that history. Any agent acting on your behalf eventually asks three questions: who is the right person, when is the right moment, and how should it reach out. Knowing who someone is can help an agent find them. Understanding how you know them can help it recognize when there’s a good reason to reach out and what you might build on.
Relationship history has to persist
An agent might learn from a meeting note that two people worked closely together. Months later, a job change might make that history relevant to a decision neither person anticipated at the time.
To connect those events, an agent needs a way to carry relationship history across conversations, update its understanding as new information arrives, and trace its conclusions back to the evidence. Each new event can change what an old relationship makes possible.
Relationships shape what becomes possible
Human relationships carry information that changes which actions are relevant, credible, and timely.
Relational contextAn employee previously worked closely with a candidate and knows the quality of their work.
Action it enablesAsk for an informed referral.
OpportunityA promising hire.
Relational contextA mutual contact knows a founder’s work and has an active relationship with an investor whose thesis fits.
Action it enablesRequest a credible introduction.
OpportunityA relevant investor conversation.
Relational contextA former customer champion joins a company facing a problem your product helped them solve.
Action it enablesReconnect with shared history and a relevant reason.
OpportunityA new customer conversation.
In each case, knowing who someone is provides a starting point. Understanding the relationships around them helps determine what to do next.
This context also changes. People move companies, priorities shift, collaborations deepen, and relationships become less active. Useful recommendations must reflect those changes.
The Dynamic Trust Graph
DeepVista is building the Dynamic Trust Graph: a structured, continuously updated record of relationships and the evidence behind them. Careers give a starting estimate. Meetings, email, and shared work correct it. An agent can then find an opportunity, explain the recommendation, and say where the evidence runs out. History stays as new evidence strengthens, qualifies, or contradicts it. Each claim records what happened, when, the source, and whether it was observed or inferred. People, organizations, and interactions form paths an agent can trace.
Experience gives a starting estimate
Careers leave a trail when meetings don’t. Three years on the same team at a 15-person startup is strong evidence; a brief overlap at a company of 8,000 is not. The estimate weighs duration, company size, proximity, role, seniority, and recency, and it is labeled inferred.
Activity turns guesses into evidence
Meetings, email, and shared documents become claims, with names resolved across sources. A shared employer stays inferred. Shipping a project together is observed.
Priya and Sam collaborated on the payments migration. Observed, meeting note, March 12, about three years of shared work.
New evidence is added beside what is already there: a job change, a long silence, a contradiction, or collaboration that upgrades an inferred overlap.
Trust is evaluated per action
The question is whether the evidence supports this action. The same relationship can pass one test and fail another. Priya can refer Sam for a staff engineer: they worked together on technical work for three years, and that was observed. She can’t make a warm intro to an investor, because there’s no evidence of an investor relationship. A reconnect after a long gap has the history, and also two years of no contact.
Paths, with receipts
The same edges form a path, including through people you haven’t worked with directly. Each step shows its evidence, whether it is observed or inferred, and how recent it is.
You to Priya to Sam. Priya and Sam worked together at Stripe for three years (observed, meeting note, March). Sam became CTO in September. They haven’t been in contact for two years (inferred from email activity). Ask Priya first.
Where the evidence runs out, the agent is designed to say so instead of guessing.
The professional network, rebuilt for agents
Every professional network today is a directory plus a feed. The platform holds the network, and an algorithm decides what you see. We expect personal agents to change who holds it, in two stages.
Who holds the network
TodayThe platform
Stage 1: better toolsThe platform
Stage 2: agent-nativeEach person’s agent
How you reach someone
TodayA cold message
Stage 1: better toolsA warm path, with evidence
Stage 2: agent-nativeYour agent asks theirs
What you see
TodayA feed an algorithm picks
Stage 1: better toolsChanges in people who matter to you
Stage 2: agent-nativeAnswers to your question
What it needs
TodayNothing
Stage 1: better toolsOne person with an agent
Stage 2: agent-nativeEnough people with agents
Stage 1
Your agent works next to the networks you already use, drawing on your own data, what’s public, and the messages you send yourself. A profile might only say Sam is a second-degree connection. Your agent can say the path runs through Priya: they worked together for three years, they haven’t spoken in two, so ask her first. That record is the graph you bring into stage 2.
Stage 2
A professional network keeps a snapshot: a title, a company, a list of connections, as of the day someone last updated it. The richer record lives elsewhere. The meetings you shared, the threads you worked through, what you built together, and when it went quiet. None of that is on the network. An agent doesn’t have to piggyback on one. It can preserve that shared context as it happens and start building it today, so by the time agents talk to each other, the history is already there.
In an agent-native network, the agents are the network. Each person’s agent holds their own relationships, knows their history and what they’re open to, and talks to other agents on their behalf. Instead of browsing profiles and a feed, you ask a question and agents answer it. This becomes possible once enough people have an agent that knows them well. In this version, the network belongs to the people in it.
Say a founder is raising a seed round. Her agent asks around:
Founder’s agent: She’s raising a seed round. Do you know an investor whose thesis fits?
Contact’s agent: He has an active relationship with Dana. I’ll check with him before I say more.
Dana’s agent: Understood. Send who vouches for the work and why it fits, and I’ll take it to Dana.
What comes back is a conclusion and the evidence for it, not the raw history. The founder gets a credible introduction. Dana gets one pitch worth reading instead of fifty cold ones. The same exchange works for a hire or a first customer.
Agents answer for the same reason people do: reciprocity. In the real world you answer a stranger because someone you trust vouched for them, or because helping builds goodwill you can draw on later. Agents can keep that memory honestly: who helped whom, how it landed, whose introductions were worth making. Answering well builds standing, and standing is what gets your own questions answered. It isn’t a score. Like everything else in the graph, it lives in each relationship.
It also changes what “warm” means. Today it means a mutual connection, which is all a network can show. With agents, warm is shared context built together: work done, a history that holds up, and a reason the request is meant for this person. That is more flexible than a connection list. A stranger with the right history can be warmer than a friend of a friend, and a close contact with nothing relevant can be colder than both.
Every person who joins makes it easier for everyone else: one more person who can confirm a history, vouch for a piece of work, or say honestly that they can’t.
It stays safe because an agent knows how well its person knows someone, and says only what that evidence supports. Agents share conclusions, not raw data, and you approve what leaves.
The graph is what both stages run on. It is designed to work for a single person, from careers and their own activity, and to get stronger as more of their network joins.
What this changes for you
Every hire, funding round, and customer starts with a relationship, and the software for relationships was built for people to browse. When everyone has an agent that knows them well, the work comes down to the same three questions: who is the right person, when is the right moment, and how should it be approached. Today the answers are scattered across your head, your inbox, your notes, and old job titles.
The Dynamic Trust Graph puts them in one place, with the evidence: a referral from someone who has seen the work, an intro through someone who knows the investor, a reconnect with a real reason.
As each person gets an agent that knows them well, those agents can connect with each other on their behalf, so the network is rebuilt around agents instead of feeds.
As agents do more of this for you, every recommendation should still trace back to its sources, and where the evidence runs out, the agent should say so.
Underneath, we think this kind of relational context will become a layer that agents across many products need. We’re starting where relationships decide the outcome: hiring, fundraising, and customers. The larger shift is in how professional networks connect.
DeepVista is building toward a future where agents help people discover opportunities grounded in their relationships, and where every recommendation has a history you can examine.
It's time for relational intelligence.
Turn your network into outcomes.
Your network already holds the opportunities. We help you find them and act on them.
No credit card required.