Full lifecycle grant platform

Find, win, and deliver on grants

epiensos watches the original sources, scores every opportunity for fit and win likelihood, and turns one click into a drafted application that never misses a deadline. After the award it tracks every deliverable, and with TALR it learns from every outcome.

Request an invitation See how it works Sign in

Simpler.Grants.govGrants.govSBIR.govNIH GuideSAM.govCDMRPNSF Seed FundFoundations

The promise

Six things it does so you do not have to

Continuous discovery

Every 6 hours from the original sources, deduplicated, with deadline changes detected.

Fit and win likelihood

A 0 to 100 fit score, a win probability anchored to the published base rate, and an expected value.

One click approval

Approve from the queue or the daily digest. The application, forms, and tasks are created for you.

AI drafted applications

Sections drafted from verified company facts, reminders at 30, 14, 7, 3, and 1 days. No missed deadlines.

Deliverables after the award

Award terms become a compliance calendar with reports generated from your own files.

Learns from every outcome

A TALR cycle on every application. Outcomes recalibrate scoring and the funder model.

The lifecycle

Discover, qualify, decide, apply, monitor, deliver, learn

One table of opportunities, one pipeline, and one loop that closes when the outcome comes back.

1 Discover
2 Qualify
3 Decide
4 Apply
5 Monitor
6 Deliver
7 Learn

01 · Discover

Continuous discovery from the original sources

A scheduled job runs every 6 hours against the official APIs and feeds. Opportunities are deduplicated by funder and opportunity number, so one notice appears once no matter how many places publish it.

Simpler.Grants.gov and Grants.gov for federal notices, SBIR.gov for open small business topics, the NIH Guide feed for notices and reissues, SAM.gov for contracts and BAAs.
HTML only sources such as CDMRP, NSF Seed Fund, Wellcome Leap, and the Michael J. Fox Foundation are scraped on a schedule, so foundation and DoD programs sit in the same table as federal grants.
Deadline changes, reissues, and expirations are detected on every run and the affected matches are rescored, so a queue never carries a dead opportunity.
Manual entry for the opportunity a program officer emailed you, with the same scoring and tracking as everything else.

02 · Qualify

Hard eligibility first, then fit

Every new or changed opportunity is scored against your company profile with a deterministic rubric and an AI written rationale. Fit score from 0 to 100, win probability anchored to the published base rate, expected value, and a plain language verdict.

Eligibility flags for entity type, size, ownership, work location, the 67 percent Phase I and 50 percent Phase II work share rules, and foreign components.
The rubric weighs programmatic fit, funder history with similar work, base rate for that institute and phase, technical readiness versus stage requested, team completeness, relationship, and time to deadline.
Strings attached are extracted from the notice: data rights, reporting cadence, cost sharing, audits, publication and data sharing, foreign disclosure.
A deliverables summary tells you what winning would obligate you to produce before you apply.

03 · Decide

One click approval with the numbers in front of you

Matches above your strictness threshold land in a queue. A daily digest emails the new ones. Each card shows fit, win probability, award ceiling, expected value, and the deadline, so a go or no go decision takes a minute, not a meeting.

A strictness slider sets the fit threshold and previews the count of queued opportunities, the sum of award ceilings, and the likely grant volume at that setting.
Approve creates the application. Decline records the reason, which feeds the next scoring calibration.
Funder history for your team is on the card: previous applications, outcomes, and total awarded.

04 · Apply

AI drafted applications that never miss a deadline

Approval downloads the forms, converts the notice into a section checklist, and drafts every section from your verified company fact library. Anything missing raises an information request assigned to the person with the right role.

Sections are drafted from facts, not invented. Each fact has an owner and a last verified date.
PDF forms are filled from sections and facts. Word and page limits are tracked per section.
An AI review panel critiques the draft against the funder's own criteria before you submit.
Submission by portal automation, email, or generated PDF, always after explicit confirmation. Files are mirrored to your Dropbox under Grants, Funder, Opportunity.
Reminders at 30, 14, 7, 3, and 1 days before every deadline, in email and in your task manager.

05 · Monitor

Inbound mail classified against open applications

A monitored mailbox is scanned every 30 minutes. Receipts, requests for just in time information, summary statements, award letters, and rejections are classified and attached to the right application, and status updates without anyone forwarding an email.

Expected decision dates on a timeline next to deadlines and award periods.
Tasks sync both ways with Melina or Todoist every 15 minutes.
Every interaction with a funder is kept, so relationship memory survives staff changes.

06 · Deliver

Deliverable tracking after the award

An award letter becomes a compliance calendar. Terms are extracted, deliverables are created with due dates, and the same reminder cadence applies to progress reports, financial reports, invention statements, and closeout.

Deliverable content is generated from the Dropbox company folder and the fact library, with information requests for anything missing.
Spend versus budget from PolyAccounts, with exceptions flagged before a report is due.
Success fee invoices are raised through Stripe only when an award is recorded.

07 · Learn

Learns from every outcome with TALR

Every application runs a Think, Act, Learn, Repeat cycle. Outcomes, reviewer scores, and summary statement critiques update the assumptions and the funder model, which feed the next Think step and recalibrate the scoring.

Predicted win probability is plotted against actual outcomes so the multiplier curve can be recalibrated.
Critiques raised independently by two or more reviewers are tagged and carried into the resubmission plan.
Weekly strategy notes summarize where the pipeline is strong, where it is thin, and what to change.

Who it is for

Built for companies, not only nonprofits

Most grant tools are shaped around 990 filings and 501(c)(3) discounts. epiensos understands the rules that decide whether a small company can even apply.

SBIR and STTR aware

Phase I, Phase II, Fast Track, Direct to Phase II, and Phase IIB mechanisms with their caps, work share rules, and submission limits.

Eligibility screening

Ownership above 50 percent by US individuals or qualifying funds, 500 employee ceiling with affiliates, place of business in the United States, for profit status.

Foreign component flags

Work location, unfunded international collaborators, foreign subawards, and the foreign disclosure form are flagged on every match before you apply.

Registrations checklist

login.gov, SAM.gov with UEI and CAGE, SBA Company Registry, eRA Commons with ORCID, Grants.gov, and Research.gov, with lead times, so a 6 week registration chain never eats a deadline.

Nonprofits are welcome too. Foundation programs sit in the same table as federal notices, and the same scoring, drafting, and deliverable tracking apply.

Works with your tools

Your files stay in Dropbox, your tasks stay where you look

Dropbox

System of record for every application and deliverable file

Todoist

Two way task sync for deadlines and information requests

Melina

Internal task driver with the same two way sync

PolyAccounts

Spend versus budget on every award, signed integration events

Gmail

Monitored mailbox classified against open applications

Stripe

Monthly subscription and success fee invoices

For AI agents

A REST API, an MCP server, and an invitation form that accepts agents

Everything a person can do in the app, an agent can do through the API. Agents can also pull AI jobs from the queue and do the drafting themselves.

REST API

JSON under https://api.epiensos.com/v1 with an OpenAPI document at /v1/openapi.json. API keys per team, scoped. Every request is one team. Lists paginate with a cursor. Money is integer minor units.

MCP server

Streamable HTTP at https://api.epiensos.com/mcp. The same operations as tools, plus two resources: the company profile and the strategy notes.

list_matchesget_matchapprove_matchdecline_matchlist_applicationsget_applicationupdate_sectionsubmit_applicationlist_deliverablesgenerate_deliverable and 9 more

Agent sign up

Tick the box on the invitation form and describe what you are. Once the team you act for is approved, an owner issues you an API key from Settings. An agent driver lets you claim queued AI jobs, complete them, and hand the result back, so a Cowork, Claude Code, or any MCP client can do the drafting instead of our provider router.

Read the agent docs agent.json llms.txt

Questions

Frequently asked

Where do the opportunities come from?

From the original sources. Simpler.Grants.gov, Grants.gov, SBIR.gov, the NIH Guide feed, and SAM.gov through their official APIs, plus scheduled scraping of HTML only programs such as CDMRP, NSF Seed Fund, Wellcome Leap, and the Michael J. Fox Foundation. Discovery runs every 6 hours.

Is epiensos for companies or for nonprofits?

Both, but it is built for companies first. It understands SBIR and STTR rules, ownership and size tests, work share percentages, foreign components, and the registration chain of SAM.gov, the SBA Company Registry, eRA Commons, and Grants.gov.

How is win probability calculated?

A weighted rubric produces a fit score from 0 to 100. The fit score is converted to a multiplier on the published base rate for that program and phase, then adjusted for resubmissions and prior awards, and clamped between 1 and 75 percent. Expected value subtracts the cost to apply and the cost of compliance.

Does the AI write the whole application?

It drafts every section from your verified company facts and raises information requests for what it cannot source. People own the scientific argument, review every section, and confirm every submission. Funder rules on AI use, including NIH NOT-OD-25-132, are surfaced on the application.

How do I sign up?

Sign up is invitation only. Request an invitation and a platform admin will release your account. People from approved organizations get immediate access after signing in at app.epiensos.com.

Can an AI agent use epiensos?

Yes. There is a REST API with an OpenAPI document, an MCP server at api.epiensos.com/mcp, per team API keys, and an agent driver that lets an external agent pull AI jobs from the queue. Agents can request an invitation with the same form.

Invitation only

Request an invitation

Sign up is invitation only while we work with early teams. People from approved organizations get immediate access after signing in at app.epiensos.com. Everyone else joins the waitlist and a platform admin releases accounts in order.