Devpost
Participate in our public hackathons
Devpost for Teams
Access your company's private hackathons
Grow your developer ecosystem and promote your platform
Drive innovation, collaboration, and retention within your organization
By use case
Blog
Insights into hackathon planning and participation
Customer stories
Inspiration from peers and other industry leaders
Planning guides
Best practices for planning online and in-person hackathons
Webinars & events
Upcoming events and on-demand recordings
Help desk
Common questions and support documentation
Sort by:
AI-powered 311 for non-emergencies. Voice-to-dispatch in less than a minute with multi-agent orchestration and ML-driven priority scoring. Turning monthlong backlogs into a day's worth of work!
MissionDeck reconciles launch evidence, asks a human for the one consequential tradeoff, and generates a cited launch pack that honors the decision.
Automate your life and work online and offline.
Authority Vision turns visual evidence into bounded agent actions—permit, hold, or human review—with observable traces, failure handling, and human control.
Your medical-bill bodyguard: an AI agent that catches billing errors, drafts the appeal, and asks you one thing — "send this?"
An agentic visual reliability engineer that uses OpenCV 5 to inspect equipment, seek better visual evidence when uncertain, diagnose faults, and trigger safe actions on AWS.
One founder. An AI organization. Ten person operating capacity.
Autonomous QA for AI coding: captures prompt intent, tests PRs via live browser journeys, and returns forensic video proof with ready-to-paste fixes.
your agent may be compromised but SENTINEL cant be SENTINEL: The Future of ai-model security
A zero-chat, semi-autonomous forensic audit system that verifies construction retainage, detects lien fraud, and enforces statutory prompt-pay deadlines before a single dollar moves.
An AI agent that remembers your loved ones for you, so distance never becomes forgetting.
GuardScale uses Amazon Bedrock to investigate server incidents, alerts you through WhatsApp and email, and turns your approved replies into scoped, temporary protection.
Relai keeps AI work moving while you’re away—safely interpreting when an agent should continue, act, or stop, so long-running tasks don’t depend on you being awake.
Sanad carries the doctor's plan between visits so no instruction, result or warning gets lost after the patient leaves.
A Strands agent that quietly turns pantry state into meal plans, shopping gaps and a safe cart draft — surfacing only decisions that actually need a person.
AuditLane makes an AI coding agent call a real human before running a command that could hurt you wired into its own execution path, so it can't skip the call.
Kujo Foreman is an autonomous release-readiness agent that verifies software changes, repairs bounded low-risk defects, and escalates only decisions that need human judgment.
A learning partner that turns any webpage - from a YouTube moment to a GitHub PR in front of you into an editable whiteboard explanation - then draws through your follow-up questions with you.
Call-E verifies whether an AI agent is actually authorised to act, enforcing bounded authority at runtime with explicit evidence, refusal, and traceable decisions.
An F1 energy strategist built on public telemetry that never fakescertainty: every number carries its provenance, its uncertainty, and theregulation version it was judged under.
In 2027 millions on Medicaid will lose coverage they still qualify for, because nobody told them to prove it. Still Covered phones them first, in their language, and hands every call to a caseworker
ClaimCall places one consented, allowlisted CALL-E call to a warranty service desk to register a consumer claim, then accepts the case reference only if it appears in the call transcript.
AuditLane calls a real human before an AI agent executes a dangerous command or trusts a claim of approval verifying, not assuming, and blocking on any contradiction.
"VentureLens turns one startup idea into a full due-diligence report — market, competitors, risk & verdict — via 6 AI agents built on AWS Strands SDK."
