Hebbia
Hebbia is an AI platform for finance and legal work whose Matrix grid resolves analytical questions across any volume of documents and whose Max analyst returns client ready spreadsheets, slides and reports, with every finding cited and auditable.
Hebbia builds AI for document heavy work in finance and law. Its two products share a design principle, which is that the analyst can trace any conclusion back to the page it came from.
Matrix is a grid. Documents form the rows, analytical questions form the columns, and the system resolves each intersection separately against that row's sources. A single instruction can produce a full workup on a company, covering valuation and growth, leverage and maturity profile, credit ratings, segment reporting, recent acquisitions, shareholder register and activist positions, governance and takeover defenses, leadership changes and strategic risks. Each answer carries the filings, transcripts and presentations it was drawn from, and the whole assembles into a slide deck. The pitch is complete traceability back to every finding, so an analyst audits rather than trusts.
Max is the conversational counterpart, an always on analyst that researches and analyzes a deal and returns client ready spreadsheets, financial models with citations in every cell, branded decks and dashboards. It works in the web app and over email, and Hebbia says a firm can turn its best processes into agents that run on their own. An integrations page connects market data from FactSet, PitchBook, S&P Capital IQ and ICE, Datasite data rooms, Snowflake and Databricks warehouses, Salesforce, Dropbox and SharePoint, all read for analysis rather than written to.
The platform is sold to investing, banking, legal and corporate finance teams, and the security posture reflects that buyer. Customer data is never used to train Hebbia's models or those of any model provider it works with. Each customer's data sits in a siloed environment isolated from every other, and Hebbia states it has no direct access to customer data, with production access restricted through just in time management.
Processing runs across the US and EU with regional options for storage and inference, and a dedicated tenant is available. Hebbia holds SOC 2 Type II and ISO/IEC 42001, is GDPR and CCPA aligned, encrypts at rest with AES-256 and in transit with TLS 1.2 or better, and publishes a trust center. Administrators can see who accessed what data, when, and what they did. Pricing is sales led.
Vendor details
Canonical URL
https://hebbia.com
Category
Enterprise operations agent
Company status
independent
Use cases & customers
In practice
A private credit team needs to pull covenants and loan terms from a portfolio of agreements before a committee meeting. Matrix reads every document and returns the terms in a cited, auditable grid.
An investment banker is prepping for a client meeting on a beverage company. They ask Matrix to synthesize key takeaways across two hundred earnings calls and filings, and it drafts a formatted brief with sources attached.
A law firm must review a hundred credit agreements for clauses that deviate from its standard template. Matrix puts the agreements in rows and the clause questions in columns, and each answer cites the agreement it came from.
Sources & related URLs
Related / legacy domains
Agentic Index coverage score
6.0 / 14 capabilities · 43%
| Integrations & Tool Calling | Partial |
|---|---|
|
An integrations page brings market data and the firm's internal data into Hebbia. It lists FactSet, PitchBook, S&P Capital IQ and ICE market data, Datasite data rooms, Snowflake and Databricks warehouses queried in plain language, Salesforce, Dropbox and SharePoint, and Max's examples also draw on Preqin and SEC filings. Every listed connection reads or searches data for the analysis. Hebbia names no write or update in an outside system, such as a posted record or a ticket, and no custom tool framework, so its output stays the spreadsheets, slides, models and reports it hands back. SourceHebbia, hebbia.com/integrations and hebbia.com/maxread 2026-11-03 |
|
| Workflow Orchestration | Full |
|
Matrix and Max both break work into many steps. Matrix is a grid where a document set forms the rows and analytical questions form the columns. In Hebbia's worked example, eighteen distinct analyses run per row, among them valuation, leverage, credit ratings, segment reporting, shareholder register, governance, leadership and risks. Each one is resolved separately against the row's sources with its own citations, and the results are assembled into a generated slide artifact, all from one instruction. The worked example uses synthetic companies, and Hebbia names no BPMN, runtime or agent count. Max researches and analyzes any deal to produce client ready spreadsheets, slides and reports, and its interface offers Auto-source and saved skills. Sourcehebbia.com/matrix and hebbia.com/productread 2026-09-12 |
|
| Knowledge Grounding & RAG | Partial |
|
Matrix reasons over a document set assembled for each task. It promises to reason over any volume of documents or companies with precise analysis and complete traceability back to every finding. In the worked example each row is scoped to a named bundle of source documents made up of 10-Qs, DEF 14As and earnings call transcripts. Hebbia names no index, graph or embeddings layer over the firm's corpus that persists and stays queryable between matrices. Sourcehebbia.com/matrix and hebbia.com/productread 2026-09-12 |
|
| Human Oversight & Guardrails | Partial |
|
Matrix is built so every finding can be checked, with complete traceability back to every finding. Each cell carries the source documents it was drawn from, and the worked example attributes each claim down to filing and date. Analysts are expected to audit results before relying on them, so a person validates each output. There is no approval queue or reviewer role, and no policy layer or administrator setting decides which outputs need sign off. Matrix and Max produce analysis and documents and take no authenticated action in outside systems. Sourcehebbia.com/matrix and hebbia.com/productread 2026-09-12 |
|
| Security, Identity & Governance | Partial |
|
The company holds SOC 2 Type II and ISO/IEC 42001:2023 and lists CCPA and GDPR alongside them. Data is encrypted with AES 256 at rest and TLS 1.2+ in transit, and Hebbia runs a trust center at trust.hebbia.ai. Under Zero-Trust Access Control, Hebbia has no direct access to customer data, and production access is restricted through just in time access management. That control covers Hebbia's own staff access to its production systems, not who inside the customer's organization can do what. Hebbia names no SSO, SAML, SCIM, OIDC or RBAC, and no roles or granular permissions. Sourcehebbia.com/securityread 2026-09-12 |
|
| Observability & Auditability | Partial |
|
Customers can see exactly who accessed their data, when they accessed it and what they did, which Hebbia pitches as complete insight into their operations. That record covers data access by people, not agent execution. Hebbia names no run trace or tool call record, and nothing on retention, export or SIEM integration. Matrix's complete traceability back to every finding is citation provenance, shown to the analyst inside a result. Sourcehebbia.com/securityread 2026-09-12 |
|
| Memory & State Persistence | Not documented |
|
No agent memory is published, whether per user or per tenant, and Hebbia names no lifetime, purge path or way to read or write one. It does not say whether conversation state carries across turns, let alone across sessions. Sourcehebbia.com/product, hebbia.com/matrix and hebbia.com/securityread 2026-09-12 |
|
| Deployment & Data Residency | Full |
|
Processing runs across the US and EU, with regional processing available for storage and inference, and Hebbia can deploy on a dedicated tenant if needed. Each customer's data is stored in siloed environments, fully isolated from every other customer. Hebbia names no on premises deployment. Sourcehebbia.com/securityread 2026-09-12 |
|
| Prebuilt Agents, Templates & Packs | Partial |
|
Max and Matrix are sold as two products. Max is an always on analyst producing spreadsheets, slides and reports, and Matrix is a grid analysis over document sets. Each does its own job. Max's interface offers a "Use a skill" action beside "Draft a presentation", "Research a topic" and "Build an Excel model". Hebbia does not say what a skill contains or where skills come from, and names no library or listing for customers to browse and adopt. Solution pages cover Investing, Banking, Legal and Corporate teams. Sourcehebbia.com/productread 2026-09-12 |
|
| Triggers & Channel Coverage | Partial |
|
Work reaches Max in two ways. A user types into the web app, or emails Max to ask a question, request a presentation or get read in before a meeting without opening the app. Matrix starts from a grid the analyst builds by adding rows and columns. Hebbia says a firm can turn its best processes into agents that run on their own, but it names no schedule, event, webhook, filing alert or inbound queue that starts them, and no Slack or Teams presence. SourceHebbia, hebbia.com/max and hebbia.com/matrixread 2026-11-03 |
|
| Model Flexibility & Routing | Partial |
|
Documents, prompts and outputs are never used to train Hebbia's models or those of any model provider it works with, and Hebbia works with more than one. Hebbia names no model picker, model policy or default override for customers or administrators, and does not name the providers it uses. Sourcehebbia.com/securityread 2026-09-12 |
|
| APIs, SDKs & MCP Extensibility | Not documented |
|
No REST or GraphQL API, SDK, developer portal (open or gated), MCP server or A2A agent card is published for calling the platform. The site has no Developers section and links no docs or developer subdomain. forum.hebbia.com is a community forum, not developer documentation. Sourcehebbia.com/product and hebbia.com/security navigation and footerread 2026-09-12 |
|
| Testing, Debugging & Optimization | Not documented |
|
Complete traceability lets an analyst check a finding by hand, one output at a time. Hebbia names no evaluation harness or scored test cases, no quality gate in a release path, no controlled experiment after deployment and no accuracy reporting for customers. Sourcehebbia.com/product, hebbia.com/matrix and hebbia.com/securityread 2026-09-12 |
|
| Browser & Computer Use | Not documented |
|
Matrix and Max work on documents supplied to them and return spreadsheets, slides and reports. Hebbia names no hosted or local browser, desktop session, or remote or local computer control. Max's Auto-source action gathers material at run time, and Hebbia does not say how. Sourcehebbia.com/product and hebbia.com/matrixread 2026-09-12 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Product updates
Hebbia now connects to Databricks, so a firm's own data such as portfolio metrics, positions and fund performance can sit in the same question as its documents, filings and licensed market data. Hebbia reads the data where it lives without copying it out. Each user signs in with their own Databricks account and sees only what they already have access to, and every answer shows its source.
Bears on: Integrations
View sourceA Datasite connector in Hebbia lets deal teams sign in with their own Datasite credentials and sync one or more virtual data room projects, bringing in only the documents each person has permission to see. Teams can then run a full diligence question list across a data room and turn the findings into a diligence summary or IC memo, with every point cited to the source page.
Bears on: Security / enterprise
View sourceHebbia released its September 2026 updates, introducing the Hebbia MCP which allows users to access Matrix and Project Intelligence directly within Claude, ChatGPT, Cursor, and internal applications. The update also enables the Max agent to generate audio briefs and interactive dashboards, and adds organizational sharing and permission controls for custom Skills.
Bears on: MCP / tool calling / API
View sourcePricing
Contact for pricing
Related vendors
- 11th Estate — Agentic platform whose AI engine scans markets, matches an…
- Abacum — FP&A platform for growing companies whose AI Modeler builds, edits…
- Adopt AI — Finance agents that categorize, reconcile and close the books inside…
- Aera Technology — Decision intelligence platform where an always on agent executes…
- Akro AI — On premise operational intelligence that automates document heavy…
- alfred_ — AI executive assistant that triages the inbox overnight and scores…
Alternatives to Hebbia
The closest documented capability profiles to Hebbia among enterprise operations agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Porters5.5 / 14Fuller documented coverage on Prebuilt Agents, Templates & Packs
- Sindri7.5 / 14Fuller documented coverage on Human Oversight & Guardrails and Prebuilt Agents, Templates & Packs
- Thefword6.5 / 14Adds documented APIs, SDKs & MCP Extensibility
- ChipAgents6.0 / 14Adds documented APIs, SDKs & MCP Extensibility
- Friendly5.0 / 14Fuller documented coverage on Knowledge Grounding & RAG
- Kenmei7.0 / 14Fuller documented coverage on Knowledge Grounding & RAG and Prebuilt Agents, Templates & Packs
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded