Company Research Brief
Know the company before the call.
Backed by Y Combinator
Accelerate your businesswith swarms of AI agents.
Create a team of self-improving agents in minutes to automate the repetitive work slowing your business down. They’re experts on day one, connect to your existing tools, and get smarter and cheaper with every run.
Get started
Copy setup instructions for your coding agent. Focus or hover to preview the guide.
Trusted by companies ready to grow faster.
From financial services to software.Meet the teams putting Grep to work.
Agent SwarmsNew feature
Put a swarm of agents to work on your backlog.
Describe the job. Your lead agent assembles a swarm of specialists to tackle it together. The swarm divides the work, shares context, and checks the results—clearing your backlog while your team handles the exceptions.
R
250+ available agents
Design your agents.
Build your swarm.
Start with an agent for the work you need done.
Account Risk Watch
Spot risk before it becomes churn.
Buyer Finder
Find the people who decide.
Batch Research Table
Compare your entire list.
Board Brief
See what matters to leadership.
Audit Readiness Checklist
Get your evidence in order.
Benchmark Watch
Track the numbers that change.
Background Pack
Get the full story.
Scale smarter. Spend less.
Consume fewer tokens as you scale
onboarding-policy.pdf
Business onboarding
Complete these checks before approving a new company.
- 01Verify the business
Confirm registration and identify beneficial owners.
- 02Review the risks
Screen sanctions lists and adverse media. Flag matches.
- 03Document the decision
Write a brief with sources and refer flagged cases for review.
Approved for team use
Your merchant classification agent is ready.
Merchant MCC classifier
Classifies merchants, cites the rules, and flags ambiguous cases.
Describe the job and share your process. Grep uses deep research to build your agent’s skills and instructions.
Illustrative workflow and costs. Actual cost depends on the task and model mix.
CUSTOMER STORY / IG
Online trading platform IG
automated 80% of onboarding.
80%
of onboarding automated
Up from 50%
3×
automated screening alert review
From 10% to 30%
<10 min
flagged customer activation
Previously 2–3 days
>99%
automated review accuracy
Reported by IG
One year in production. Zero production issues reported.Reported by IG
Manage agents
across your enterprise.
Deploy your agent workforce across teams with centralized permissions, budgets and oversight. Share and version agents, inspect every run and file, and keep control of your data.
One system. Every agent.
Agent OS
From the first instruction to every production run.
Agent orchestration
Route work to the right agents and models across your organization.
Model cost optimization
Use smaller models for repeated work and frontier models for judgment.
Isolated execution
Run each job in a fresh sandbox, separate from other agent runs.
Run history & file access
Inspect jobs, retries and outputs. Access every file the agent used.
Permissioned data access
Connect 100+ built-in sources and your own data with scoped access.
Budgets & spend visibility
Set limits per run and track spending across your agent workforce.
Role-based access control
Control who can view, edit and run agents, and access their files and reports.
Scoped credentials
Grant least-privilege access. Rotate or revoke credentials anytime.
Agent audit logs
Review every step, tool call and model choice. Export the audit trail.
SOC 2TYPE II
Type II compliant. Annual third-party penetration tests.
No training on your data
Your data is not used for training. Control retention and deletion.
Shared agents & version control
Share and edit agents across teams, with full version history.
05 / CONNECTED TO YOUR WORK
Connect your APIs, MCPs, and webapps.
Connect to over 1,000 applications and tools, add your own APIs and MCP servers, or work in your webapps through authenticated browser sessions.
Connect your toolsYOUR TOOLS. CONNECTED TO YOUR AGENTS.
Or use 100+ built-in integrations.
Ready-to-use data sources for your agents, from company registries and sanctions lists to courts and market data. No accounts to connect or logins required.
Your data sources. Already connected.
USPTO
OpenCorporates
ComplyAdvantage
Zillow
OpenSanctions
Trustpilot
Amadeus
Semantic Scholar
PubMed
Crunchbase
Middesk
Finnhub
LEI / GLEIF
Yelp
FRED
GDELT
arXiv
LinkedIn
MarineTraffic
CoinMarketCap
PIPL
ImportGenius
EPO
People Data Labs
Frequently asked questions
Is this a model gateway or a router?
No. A gateway forwards your tokens to whichever model you name; a router load-balances. Grep runs the entire job. It picks the model for each step against your cost ceiling and accuracy floor, executes in isolated sandboxes, and writes the audit trail. The model choice is an output, not your input.
Do I have to talk to sales to try it?
No. Self-serve signup runs an agent the same day, no sales contact. Self-serve is a headline feature, not a consolation path. Enterprise teams spending $50K+/month get a working session. The product is never gated or waitlisted.
Which models do you use?
Claude, GPT, DeepSeek, and secure open-source models, chosen per step. Cheap, fast models handle ingestion and extraction; frontier models are reserved for the steps where accuracy is non-negotiable. You set the constraints; the harness routes.
How is “managed” different from a provider’s managed offering?
A provider optimizes for its own models. It wins when you spend more on them. Grep is not a model. We optimize across all of them for your constraints, and we win when you win. Managed is not Claude-managed.
What do you give compliance and risk teams?
A decision trail on every run: the model chosen, the cost, and the reason for each step, exportable as a file you can hand to a regulator. Sandbox isolation, scoped keys, and SOC 2 Type II compliance are standard.
How does pricing work?
See pricing for current plans, or contact our team to discuss enterprise requirements.
SWARMS BY GREP AI