# Amazon Bedrock Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/amazon-bedrock
> Markdown URL: https://aitinkerers.org/technologies/amazon-bedrock.md
> Technology record last updated: 2026-02-26T09:14:23Z
> Generated: 2026-09-21T13:43:18Z

Amazon Bedrock is the fully managed, serverless service for building and scaling generative AI applications with a choice of high-performing foundation models via a single API.

Bedrock is the AWS fully managed service for enterprise-grade generative AI: it delivers a single, consistent API to access a wide selection of top Foundation Models (FMs). This includes models like Anthropic's Claude 3, Meta's Llama 2, and Amazon's Titan family . Developers can privately customize these FMs using their own data via techniques like fine-tuning and Retrieval Augmented Generation (RAG) . Bedrock also provides essential builder tools, including Agents for complex task orchestration and Guardrails for implementing application-specific safety policies . The serverless experience removes infrastructure management, letting teams focus entirely on application logic and deployment .

- Official technology site: https://aws.amazon.com/bedrock/
- Public AI Tinkerers demos and talks: 20
- Result page: 1 of 1

## Recent Public Talks and Demos

### [AI Powered Company Evaluation & Coaching](https://cairo.aitinkerers.org/talks/rsvp_erT3jGWE7MU)

VCDNA is a multi-agent platform that evaluates and coaches the companies companies you consider - turning each into a consistent, evidence-traced, IC-evidence-traced, IC-ready assessment.

- Event context: AI Tinkerers Cairo: Inaugural Meetup — 2026-07-01 — Cairo
- Public talk page: https://cairo.aitinkerers.org/talks/rsvp_erT3jGWE7MU

### [Building a production GTM agent: what broke and how we fixed it](https://boston.aitinkerers.org/talks/rsvp_KyMpqyZSw7M)

We built a GTM agent that runs outbound end-to-end. The agent finds prospects in your ICP, comments on their LinkedIn posts, sends connection requests and messages, and books meetings for you. I can share how the agent works and walk through the architecture, including things like: - how we decide which parts of the workflow should be handled by an agent versus deterministic code - how we store structured state in Postgres so the agent can keep track of prior actions and workflow progress - how we built human-in-the-loop review so users can approve actions before the agent proceeds - how the workflow pauses and resumes across long-running tasks I can also show a few examples of where the system initially broke and what we changed to make it more reliable in production.

- Event context: AI Tinkerers Boston: GTM Agentic AI Launch — 2026-06-29 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_KyMpqyZSw7M

### [GTM in the Terminal — Agent-driven personalized outbound](https://sf.aitinkerers.org/talks/rsvp_O2H7CQUJ6IU)

Cyrus is the cofounder of The Synthesis Company (YC S24). Previously, he was a core contributor to Stanford NLP's DSPy framework and cofounder of WOMBO.ai (100M+ downloads). He'll be demoing GTM-OS, a CLI and TUI he used to programmatically drive hyper-personalized LinkedIn outbound. For AI tinkerers he built usesocial.dev, a CLI to connect your agents to LinkedIn / X and build your own workflows and systems.

- Event context: AI Tinkerers San Francisco: GTM Engineering Track — 2026-05-19 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_O2H7CQUJ6IU

### [AI for people who still print their email: how we put a 25-tool agent in front of 50-year-old accountants without a single hallucinated delete](https://poland.aitinkerers.org/talks/rsvp_d3AEfot6ruQ)

Numonis is an accounting SaaS in Spain and Portugal where the primary users are 40–60-year-old SMB owners and accountants, and we shipped a pydantic-ai conversational agent with 25+ tools (invoicing, documents, banking, P&L, tickets) as the main interface. Live demo: I run a demo of the system's features all over one typed SSE stream. Between beats I flip to DevTools to show the raw frames so the wire protocol is visible end to end.

- Event context: AI Tinkerers Poland #3 - Meetup in Wrocław — 2026-05-06 — Poland
- Public talk page: https://poland.aitinkerers.org/talks/rsvp_d3AEfot6ruQ

### [0 Stars, 10/10: A Multi-Agent Pipeline That Makes a Podcast Every Week](https://dc.aitinkerers.org/talks/rsvp_VuQRBz6hhMM)

A closed-loop multi-agent system on AWS that produces a comedy podcast every week without human involvement. Seven agents orchestrated by Step Functions discover underrated GitHub projects, research the developers, write a three-persona comedy script, evaluate it against a quality rubric (with automatic rewrites on failure), generate cover art, produce audio, and publish the episode. Three AI personas debate each project: an overly optimistic hype beast, a dry British cynic, and an existential philosopher. The pipeline learns from its own LinkedIn engagement metrics to bias future episode selection toward what actually performs well. I'll play the first episode and walk through the agent coordination that produced it.

- Event context: AI Tinkerers x Softengi - DC Metro Meetup - April 9th, 2026 — 2026-04-09 — DC
- Public talk page: https://dc.aitinkerers.org/talks/rsvp_VuQRBz6hhMM

### [Bmg usa IA para análise e padronização de documentos em larga escala, e atende órgão regulador.](https://saopaulo.aitinkerers.org/talks/rsvp_PNWm4hcTjqE)

O projeto é um agente de Inteligência Artificial desenvolvido para automatizar a análise, organização e padronização massiva de documentos de seguros: - O contexto prático da aplicação envolveu a necessidade urgente do Banco Bmg (BMG Seguradora) de processar e validar aproximadamente 6 anos de histórico de dossiês para atender a uma exigência de um órgão regulador, uma tarefa de escala tão grande que tornava o cumprimento do prazo inviável por vias puramente manuais

- Event context: AI Tinkerers SP e Banco BMG — 2026-03-26 — São Paulo
- Public talk page: https://saopaulo.aitinkerers.org/talks/rsvp_PNWm4hcTjqE

### [Cache-Optimized Agentic Fanout: Squeezing 65x More Intelligence Per Dollar From Claude](https://chicago.aitinkerers.org/talks/rsvp_0Ru5Zk7StVE)

We got a 65x reduction in per-rule input cost by designing the prompt architecture around Anthropic's cache economics — and the constraints that forced are more interesting than the savings. Live demo of a production system that evaluates 50+ natural-language compliance rules against 100+ page financial documents. Each rule needs full document context (~32k tokens), so naive execution is a non-starter on cost and rate limits. The fix: append-only message threads where nothing is ever mutated or removed, because any change to the prefix — including the tool schema — invalidates the cache. Tools that should not fire are rejected with a reply prompt, not removed from the definition. A warming request primes the cache before the real fanout begins. pg-boss orchestrates the map-reduce: Phase 1 parses documents in parallel via Reducto, Phase 2 fans out N independent agent invocations (one per rule, configurable concurrency per ECS task), Phase 3 reduces to review status. After the first cache write, subsequent rules pay ~500 new tokens instead of ~32k (!!!). The agent has four tools that persist directly to Postgres with no post-processing step: Think (structured reasoning), Calculate (mathjs-backed arithmetic verification), AnnotationWrite (bounding-box PDF evidence traceable to specific parsed document blocks), and RecommendationWrite (PASS/FAIL with confidence). Full OTel instrumentation with GenAI semantic conventions traces every tool call, token count, and cache hit/miss.

- Event context: AI Tinkerers Chicago: March Meetup ft. Programmers Inc. — 2026-03-17 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_0Ru5Zk7StVE

### [Routing to the right LLMs, dynamically than hard coding. Catching Cost issues in the code](https://ho-chi-minh-city.aitinkerers.org/talks/rsvp_-KpxPGzcak8)

I will present 2 developer centrics solutions - 1. CloudVerse AIX - dynamically routing to the correct LLMs under cost, latency, qualty and compliance constraints, than hardcoding LLMs. This solution tracks over 600 Models globally and can route to any under controlled directions. 2. CloudVerse DevX - DevFinOps AI bot. The bot sits inside repos, CLIs and AI agents, identified cost issues in code at the time of commit or PRs. The prevents costly issues from entering into production.

- Event context: AI Tinkerers Ho Chi Minh City: From Prompt to Agent — 2026-03-07 — Ho Chi Minh City
- Public talk page: https://ho-chi-minh-city.aitinkerers.org/talks/rsvp_-KpxPGzcak8

### [Code Less, Create More: AI's productivity Revolution](https://manchester-nh.aitinkerers.org/talks/rsvp___SyeaCKrk0)

In this demonstration we'll explore how organizations are leveraging AI-powered development tools to accelerate delivery, reduce technical debt, and empower their workforce to shift from their role as just "code writers" and "programmers" to innovators. We'll examine real-world examples of productivity gains, discuss the paradigm shift in how we approach software development, and reveal how organizations are reclaiming time for their teams to do what humans do best—think creatively, collaborate meaningfully, and drive transformational change

- Event context: AI Tinkerers – Manchester/Bedford Inaugural Meetup · January 20, 2026 — 2026-01-20 — Manchester NH
- Public talk page: https://manchester-nh.aitinkerers.org/talks/rsvp___SyeaCKrk0

### [Proactive AI Teammate that evolves with your team](https://nyc.aitinkerers.org/talks/rsvp_Kea85Vzg8pI)

We showcase how Teamate, a proactive AI assistant that's designed to work natively with a team, can chime in at the right moment to provide your team with just the right context. We also showcase how it can carry out tasks on behalf of the team, and how it can recall relevant facts so your team can eventually replace your CRM with it.

- Event context: Auth0 x AI Tinkerers: Fall Social Demo Night 🍁 ft. Hex — 2025-11-06 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_Kea85Vzg8pI

### [Healthcare Agents](https://nashville.aitinkerers.org/talks/rsvp_XZW4s8Lqt1A)

we have bedrock documentation agents, UIs that talk to bedrock as a chat interface, and quite a bit of MCP tooling so any of those parts

- Event context: AI Tinkerers Nashville – October 28th, 2025 — 2025-10-28 — Nashville
- Public talk page: https://nashville.aitinkerers.org/talks/rsvp_XZW4s8Lqt1A

### [An agentic autonomous prompt optimization and model selection tool/gateway](https://dc.aitinkerers.org/talks/rsvp_kecnsJJpcAo)

We'll demonstrate an agent that analyzes LLM traces and recommends optimal models and LLM usage recommendations to aid in model selection, performance optimization, and cost reduction, and how this can be used in an intelligent AI router.

- Event context: AI Tinkerers x Google: DC Metro Meetup (October 2, 2025) — 2025-10-02 — DC
- Public talk page: https://dc.aitinkerers.org/talks/rsvp_kecnsJJpcAo

### [AI/ML for SMBs](https://atlanta.aitinkerers.org/talks/rsvp_ODG8dpI77oo)

How to leverage AI/ML to drive automate routine tasks like data entry and scheduling, generate content for marketing, and enhance customer service through chatbots and personalized recommendations.

- Event context: AI Tinkerers Atlanta Meetup – August 28, 2025 — 2025-08-28 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_ODG8dpI77oo

### [Building 'mission control' for software engineering agents](https://london.aitinkerers.org/talks/rsvp_ufx_6-dsLjY)

Live demo showing how Ona orchestrates software engineering agents working in parallel on engineering tasks. I'll walk through the technical architecture of isolated and ephemeral agent/human environments - show how agents securely execute code changes and demonstrate the integration with editors, source control, secrets managers etc.

- Event context: AI Tinkerers London Meetup - 28th August 2025 — 2025-08-28 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_ufx_6-dsLjY

### [AutoGrading Student Answers using](https://dubai.aitinkerers.org/talks/rsvp_nZAAyR1_6s0)

I implemented a full scale autograding solution for written and spoken answers for 1million userbasr 25k concurrent users. We used whisper and llama. On different providers to meet the scale.

- Event context: AI Tinkerers Dubai Meetup — August 2025 Demo Day — 2025-08-23 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_nZAAyR1_6s0

### [Recent Announcements from AWS](https://singapore.aitinkerers.org/talks/rsvp_UQvikC78n90)

We will cover quick demos of Kiro (agentic coding IDE), AgentCore (new purpose-built agentic foundational services from AWS) and Strands SDK (open source SDK for building agents).

- Event context: AIT Singapore: scalable agentic workflows - 12th August 2025 — 2025-08-12 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_UQvikC78n90

### [Voice Assistants made easy with Amazon’s new Nova Sonic foundation model](https://miami.aitinkerers.org/talks/rsvp_V95wr3ftOME)

Description: Explore a real-time, bidirectional speech interactions using cutting-edge foundation models. Learn how to create fluid, natural-sounding voice applications that respond intelligently in real-time. For developers and architects interested in conversational AI applications with state-of-the-art voice technology. Code samples and implementation guidelines will be provided to help you get started with your own voice-enabled projects. Technical Prerequisites: - Programming experience - Basic understanding of audio processing concepts - Basic understanding of Foundation Models

- Event context: AI Tinkerers - Miami: Building the Future of AI in Miami Tech — 2025-04-22 — Miami
- Public talk page: https://miami.aitinkerers.org/talks/rsvp_V95wr3ftOME

### [Build Performant RAG Applications Using Couchbase Vector Search and Amazon Bedrock](https://dubai.aitinkerers.org/talks/rsvp_o0yX8-d4oCo)

This demo showcases how to build a Retrieval-Augmented Generation (RAG) application using a vector database and Amazon Bedrock. The process begins with creating a vector index in the vector database to store, index, and retrieve embeddings efficiently. Amazon Bedrock is then integrated to access foundation models like Anthropic Claude for embeddings and large language model (LLM) responses. The demo also highlights the development of a production-grade RAG pipeline using orchestration frameworks such as LangChain or LlamaIndex. By combining vector search capabilities with foundation models, this approach enables highly granular and contextually accurate applications across industries, supporting use cases like content creation, question answering, summarization, and report generation.

- Event context: AI Tinkerers Dubai - April 2025 - Demos Night! — 2025-04-11 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_o0yX8-d4oCo

### [Enhancing GenAI to take real-world actions with Amazon Bedrock agents & Powertools](https://dubai.aitinkerers.org/talks/rsvp_3HOtj7mSLyc)

This presentation demonstrates how to combine the reasoning capabilities of Bedrock with custom business logic, allowing LLMs to interact with your systems and execute real-world tasks." We will demonstrate a fictional helpdesk chatbot that not just helps in resolving user issues, but can also interact with third party services to allow it to create and update tickets. Using Bedrock and Lambda we demonstrate how you can build simple integrations without deploying any infrastructure. In addition, we will give an overview of the Lambda powertools event handler to automatically generate OpenAPI schemas and abstract request routing to simplify agent group configuration. "Discover how to extend the capabilities of Foundation Models beyond content generation by enabling them to perform concrete actions through Amazon Bedrock Agents. This presentation demonstrates how to combine the reasoning capabilities of Large Language Models with custom business logic, allowing AI to interact with your systems and execute real-world tasks."

- Event context: AI Tinkerers - Dubai Meetup #5 (February) — 2025-02-05 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_3HOtj7mSLyc

### [Orchestrating serverless generative AI applications](https://dubai.aitinkerers.org/talks/rsvp_VmIa7QTp02E)

In the journey to build versatile serverless generative AI applications, discover the roadmap from concept to realization, all within an efficient, model-driven design setup. From principles to prototyping with the tools, learn how to bring your ideas to your users in a scalable, efficient manner. This demo will show how one can leverage using Amazon Bedrock and the models available on it, while orchestrating the steps visually using AWS Step Functions.

- Event context: AI Tinkerers - Dubai Meetup #2 (October) — 2024-10-05 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_VmIa7QTp02E

## Related Technologies

- [AWS Lambda](https://aitinkerers.org/technologies/aws-lambda) ([Markdown](https://aitinkerers.org/technologies/aws-lambda.md)) — 14 public demos
- [AWS Step Functions](https://aitinkerers.org/technologies/aws-step-functions) ([Markdown](https://aitinkerers.org/technologies/aws-step-functions.md)) — 3 public demos
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 173 public demos
- [Claude Sonnet 4](https://aitinkerers.org/technologies/claude-sonnet-4) ([Markdown](https://aitinkerers.org/technologies/claude-sonnet-4.md)) — 18 public demos
- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 445 public demos
- [LLM](https://aitinkerers.org/technologies/llm) ([Markdown](https://aitinkerers.org/technologies/llm.md)) — 123 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [Vertex AI](https://aitinkerers.org/technologies/vertex-ai) ([Markdown](https://aitinkerers.org/technologies/vertex-ai.md)) — 31 public demos
- [AgentCore](https://aitinkerers.org/technologies/agentcore) ([Markdown](https://aitinkerers.org/technologies/agentcore.md)) — 1 public demo
- [AI](https://aitinkerers.org/technologies/ai) ([Markdown](https://aitinkerers.org/technologies/ai.md)) — 55 public demos
- [AI Foundry](https://aitinkerers.org/technologies/ai-foundry) ([Markdown](https://aitinkerers.org/technologies/ai-foundry.md)) — 2 public demos
- [Amazon EC2](https://aitinkerers.org/technologies/amazon-ec2) ([Markdown](https://aitinkerers.org/technologies/amazon-ec2.md)) — 7 public demos
- [Amazon Kinesis](https://aitinkerers.org/technologies/amazon-kinesis) ([Markdown](https://aitinkerers.org/technologies/amazon-kinesis.md)) — 5 public demos
- [Amazon S3](https://aitinkerers.org/technologies/amazon-s3) ([Markdown](https://aitinkerers.org/technologies/amazon-s3.md)) — 8 public demos
- [Amazon SageMaker](https://aitinkerers.org/technologies/amazon-sagemaker) ([Markdown](https://aitinkerers.org/technologies/amazon-sagemaker.md)) — 2 public demos
- [Anthropic API](https://aitinkerers.org/technologies/anthropic-api) ([Markdown](https://aitinkerers.org/technologies/anthropic-api.md)) — 66 public demos
- [AWS](https://aitinkerers.org/technologies/aws) ([Markdown](https://aitinkerers.org/technologies/aws.md)) — 38 public demos
- [AWS Lambda Powertools](https://aitinkerers.org/technologies/aws-lambda-powertools) ([Markdown](https://aitinkerers.org/technologies/aws-lambda-powertools.md)) — 1 public demo