# Claude Sonnet Projects at AI Tinkerers > Canonical HTML: https://aitinkerers.org/technologies/claude-sonnet > Markdown URL: https://aitinkerers.org/technologies/claude-sonnet.md > Technology record last updated: 2026-09-18T15:13:41Z > Generated: 2026-09-20T20:45:42Z Claude Sonnet 4.5 is Anthropic's premier model: state-of-the-art for agentic coding, computer use, and complex, long-horizon workflows. Claude Sonnet 4.5 is engineered for superior agentic performance, excelling in complex, multi-step workflows across coding, finance, and cybersecurity (e.g., achieving a 77.2% score on SWE-bench Verified). This model offers a powerful balance of speed and cost: it is priced at $3 per million input tokens and supports a massive 200,000-token context window. This capacity allows for sustained reasoning, with internal tests confirming the model maintains focus for over 30 hours on demanding tasks. It is available via the Claude API, Amazon Bedrock, and Google Cloud's Vertex AI, making it the top choice for developers building robust, production-ready AI agents. - Official technology site: https://claude.ai - Public AI Tinkerers demos and talks: 20 - Result page: 1 of 1 ## Recent Public Talks and Demos ### [Michi — giving a face to a conversational AI model](https://tokyo.aitinkerers.org/talks/rsvp_s9Dq_V1NOf8) Michi is a voice-first conversational travel concierge built at the Perxona hackathon. Users talk with a 3D avatar to explore Tokyo activities, revise preferences in real time, and build an itinerary through natural conversation. A language model manages the dialogue and produces structured proposals, while a deterministic TypeScript engine controls retrieval, eligibility, scheduling, availability, and pricing against a bounded activity catalogue. Local text and audio models help adapt Michi’s delivery without influencing planning decisions. - Event context: AI Tinkerers Tokyo - September 1st Meetup — 2026-09-01 — Tokyo - Public talk page: https://tokyo.aitinkerers.org/talks/rsvp_s9Dq_V1NOf8 ### [Stop Re-Reading Your Conference Notes: Build a Spaced-Repetition Course Instead.](https://columbus.aitinkerers.org/talks/rsvp_-a2BC9vkaEk) A personal learning platform that turns everything I captured at AI Engineer World's Fair 2026 (53 talk transcripts, wearable-recorder audio, 167 photos and videos) into a keyboard-first spaced-repetition course, built almost entirely by an orchestrated fleet of Claude agents. I started by researching the learning-science literature (retrieval practice, FSRS spaced repetition, the Feynman technique) and encoded those techniques as the product spec. Then agents matched my camera roll to the conference schedule, wrote 66 lessons across two courses (the conference itself, plus a formal-methods course from a folder of university PDFs), generated 274 retrieval cards, and typeset real MathML formulas. Everything compiles to one dependency-free HTML file with an FSRS-5 scheduler I implemented from the published weights. I'll demo the working system live: the review queue, my own conference photos matched to the right talks, clickable scholar bios, and the generator pipeline that lets agents write validated JSON instead of HTML. - Event context: AI Tinkerers - Columbus August Meetup — 2026-08-03 — Columbus - Public talk page: https://columbus.aitinkerers.org/talks/rsvp_-a2BC9vkaEk ### [Agent Memory Is the Softest Attack Surface. Let Me Show You.](https://minneapolis-saint-paul.aitinkerers.org/talks/rsvp_vxTZZYnTRxQ) A memory-enabled AI financial advisor for small businesses that remembers each customer across sessions. The app is just the testbed. The real subject is agent-memory security: what breaks when you give an agent long-lived, multi-tenant memory. It runs on a real stack, with vector-searched long-term memory, per-tenant isolation, and live similarity scores on screen. In the demo I show it working, then run two live attacks on its memory: a cross-tenant data leak on the read path, and a persistent memory-poisoning injection on the write path. Then I show the defense for each. Everything is live: the working system, the memory recall panel, the one line of code that is the entire tenant boundary, and the toggles that break and fix it. No slides. Synthetic data only. - Event context: AI Tinkerers Minneapolis-Saint Paul — July Meetup — 2026-07-29 — Minneapolis Saint Paul - Public talk page: https://minneapolis-saint-paul.aitinkerers.org/talks/rsvp_vxTZZYnTRxQ ### [The Interview That Runs Itself](https://seattle.aitinkerers.org/talks/rsvp_HVXP2AFZt-U) I built a brand-discovery workshop that runs itself: an ElevenLabs voice agent interviews you about your brand, and while you're still talking, Claude mines the live transcript and pops "nuggets" (quotable insights) onto the screen in real time — then turns each section of the conversation into structured deliverables: a brand voice guide, an ICP profile, and a channel strategy. I used to run this workshop by hand — 90 minutes per client plus waiting on transcripts — so I automated the interviewer out of the room, starting with me. Live, I'll talk to the agent on stage so you can watch insights get captured mid-sentence, walk the two-model architecture on an interactive deck that replays a real session using the app's actual pacing and threshold code, and show the working system deployed at workshop.trymarketingmachine.com. - Event context: AI Tinkerers Seattle Summer Bash — 2026-07-29 — Seattle - Public talk page: https://seattle.aitinkerers.org/talks/rsvp_HVXP2AFZt-U ### [Multi-Pass Building Defect Detection: Getting a VLM to Find Facade Defects for Visual Inspections](https://dc.aitinkerers.org/talks/rsvp_3zzrUv1SHxo) We built an AI system that turns raw building inspection photos into annotated defect reports, detecting 15 distinct pathologies (building cracks, sealant degradation, brick spalling, mortar erosion, steel corrosion, and so on) with accurate bounding boxes across facade inspections. I'll show the architecture of how we've setup the inspection image processing pipeline: the multi-pass detection architecture, the model training process, the defect annotation catalog, the eval harness we use to verify accuracy on new datasets & catch regressions. And why this was our selected way to set it up. I'll walk through the examples of real reports going from photo dump to structured outputs (where the model gets it right and where it still needs a human check). - Event context: AI Tinkerers DC Metro - Arlington: July 23rd Meetup — 2026-07-23 — DC - Public talk page: https://dc.aitinkerers.org/talks/rsvp_3zzrUv1SHxo ### [Meetings, Market Signals, and Messy Data: Building an AI Intelligence Platform](https://orange-county.aitinkerers.org/talks/rsvp_-wH-ikAKux0) An AI-powered internal platform that ingests data from Zoom transcripts, internal knowledge bases, and external market signals, processes it through Claude AI, and stores the enriched intelligence in SingleStore — so we can proactively manage client relationships instead of reacting to them. - Event context: AI Tinkerers Orange County: Tuesday, July 21, 2026 at Centercode — 2026-07-22 — Orange County - Public talk page: https://orange-county.aitinkerers.org/talks/rsvp_-wH-ikAKux0 ### [Verification with LLM powered Behavior Driven Development (BDD)](https://seattle.aitinkerers.org/talks/rsvp_abgJncjsLmk) At SageOx, we've built test tooling that has raised the conceptual level of E2E tests from traditional code to human natural language. We've married the old idea of BDD (Behavior Driven Development) with LLMs to reduce the cognitive debt of designing and reviewing acceptance criteria for agent generated code. In my demo, I will show you a test scenario can be defined using natural language in the Gherkin format, have a coding agent turn that into a test run plan that exercises our Web UI, CLI and integration in Claude Code. And, then show a trace of the test running against these multiple interfaces in a single pleasing test report. - Event context: AI Dev Tools Track - Seattle - July 13 — 2026-07-14 — Seattle - Public talk page: https://seattle.aitinkerers.org/talks/rsvp_abgJncjsLmk ### [From Dashboards to GTM Action Loops](https://boston.aitinkerers.org/talks/rsvp_k0m7uHbc2O8) We built a GTM insight reporting agent on Squadbase for RevOps, CS, and Marketing teams. It monitors dashboards, finds meaningful changes, investigates the cause, and turns the result into a short report with recommended next actions. The report is not the end of the workflow. A team member can open it, review the dashboard, check the agent trace, and keep digging into the source data with the same context. In the demo, I will show a dashboard change, the agent’s SQL/TypeScript investigation, the cause analysis, and the final report that helps a GTM team decide what to do next. - Event context: AI Tinkerers Boston: GTM Agentic AI Launch — 2026-06-29 — Boston - Public talk page: https://boston.aitinkerers.org/talks/rsvp_k0m7uHbc2O8 ### [Graph-Oriented Generation: Deterministic Context Retrieval for Code](https://manchester-nh.aitinkerers.org/talks/rsvp_SMbTB_Lslqs) GOG (Graph-Oriented Generation) is a deterministic context-retrieval system for code generation: instead of embedding chunks and pulling them by similarity, it parses the codebase into an AST-derived graph and traverses it to assemble precise context for a prompt. Live, I'll run the same prompt through Claude Code two ways — vanilla, and with GOG injecting context — and walk the full path from the initial prompt, through decomposing the project structure into stratum relationships, to the actual AST graph traversal that selects what the model sees. You'll see the retrieval working, not a slide about it. - Event context: AI Tinkerers Manchester (Bedford), NH - June 2026 Meetup — 2026-06-17 — Manchester NH - Public talk page: https://manchester-nh.aitinkerers.org/talks/rsvp_SMbTB_Lslqs ### [Merging Multi Agent Council Delibrations with Dynamic Analytics to Redesign Transit Infrastructure](https://toronto.aitinkerers.org/talks/rsvp_zWQT1Z51PV8) A sandbox planning tool where you draw new Toronto transit lines and a 6-agent AI council critiques it; with the ability to see real-time changes and analytics for routes and ridership as the line is developed. - Event context: AI Tinkerers Toronto - April 2026 - hosted by Shopify — 2026-04-29 — Toronto - Public talk page: https://toronto.aitinkerers.org/talks/rsvp_zWQT1Z51PV8 ### [shelf: autoresearch for Shopify storefronts](https://toronto.aitinkerers.org/talks/rsvp_oVI3sYF9QNQ) shelf is an open-source CLI that applies the autoresearch loop (the same pattern Tobi Lutke used to make Liquid 53% faster) to Shopify product catalogs. Instead of optimizing build time, it optimizes AI discoverability. It generates shopper queries, asks them to real AI agents via their APIs, scores how often your products surface, proposes one atomic catalog change, applies it via Shopify's Admin GraphQL API, re-scores, and keeps or reverts. It runs until you tell it to stop. - Event context: AI Tinkerers Toronto - April 2026 - hosted by Shopify — 2026-04-29 — Toronto - Public talk page: https://toronto.aitinkerers.org/talks/rsvp_oVI3sYF9QNQ ### [Your GTM Copy Only Reaches 32% of Buyers — Here's How to Measure It](https://seattle.aitinkerers.org/talks/rsvp_UuJIGqJNdf0) COS is a content measurement engine that scores how well B2B sales and marketing copy resonates across all five buyer personality types (Big Five/OCEAN). It orchestrates 7 parallel analysis frameworks through a 24-module knowledge base (~38K lines of psychology research) to surface which buyer segments you're reaching and which you're missing. Live at cos.semalytics.com, free guest mode, no signup. - Event context: AI Tinkerers Seattle: GTM Engineering — April Meetup — 2026-04-23 — Seattle - Public talk page: https://seattle.aitinkerers.org/talks/rsvp_UuJIGqJNdf0 ### [From Abacus to AI: Small Potatoes, Big Results](https://hong-kong.aitinkerers.org/talks/rsvp_3XIaboEtPiM) I'll share my real, month-long journey as a complete non-coder who used today's AI tools (like Grok, Copilot, Claude Haiku, and especially Claude Sonnet) to build actual working things: two World of Warcraft in-game addons for my uncles to track character stats and items automatically, a "Next Bus" app for our island's private bus routes (pulling schedules from PDFs and images), and a simple dinner-bell phone app that rings my phone when someone hits bell button their phone. The talk walks through the messy reality — starting with total confusion (SQL commas feeling like ancient abacus work, AWS looking like a blurry PS2 game, pasting code line-by-line and debugging parentheses I didn't understand), failing a lot, switching models when one got stuck, and eventually getting functional apps and addons. I'll show how I "failed faster" by iterating quickly, using my own low-tech version control (100+ numbered folders), and leaning on different AIs for different strengths. It's not about becoming a pro developer overnight — it's about an ordinary person getting useful results with zero prior experience. - Event context: AI Tinkerers Hong Kong GBA at the Hive: Creative AI Demos & Technical Show-and-Tell — 2026-03-26 — Hong Kong - Public talk page: https://hong-kong.aitinkerers.org/talks/rsvp_3XIaboEtPiM ### [CyberSentinel: Building a Threat Detection Pipeline](https://miami.aitinkerers.org/talks/rsvp_8u_zBunWIJ0) CyberSentinel is a multi-stage security analysis pipeline. It ingests raw logs from firewalls, SSH, web servers, and intrusion detection systems, identifies threats, maps them to MITRE ATT&CK and the Cyber Kill Chain, and generates a report with severity scores and indicators of compromise. For the live demo, I'll run it against a simulated 5-phase attack (port scanning, SSH brute force, background noise, SQL injection, data exfiltration) and show how 458 log lines become 2 correlated threat clusters and 12 IOCs in under 2 seconds. - Event context: AI Tinkerers Miami: Spring Demos at The Lab — 2026-03-25 — Miami - Public talk page: https://miami.aitinkerers.org/talks/rsvp_8u_zBunWIJ0 ### [Kokoro on the web](https://la.aitinkerers.org/talks/rsvp_iMNQYyRB6MM) Expanded my iOS app for summarizing any article into 3 levels of detail, into a web app so Android users can use it. To save money I’ve got a free (for low usage) PaaS running Kokoro (the same TTS I’m running directly on the iPhone). Shocking how much cheaper it is, even at usage beyond free level. Also found my existing prompts (Llama 3.2 and Apple Intelligence on iOS, as well as Claude Sonnet via API) have consistent accuracy issues, which I’m still working on. - Event context: AI Tinkerers LA: February Builder Meetup & Live Demos — 2026-02-24 — Los Angeles - Public talk page: https://la.aitinkerers.org/talks/rsvp_iMNQYyRB6MM ### [Building a 10¢ Research Paper TTS Pipeline: Kokoro, Claude, and the Hidden Costs of Audio](https://la.aitinkerers.org/talks/rsvp_wigMst0JqyA) I built a native iOS + web app that turns research papers into listenable audio summaries in ~30 seconds. The stack: Claude Sonnet for summarization, Kokoro TTS (82M parameter on-device model) for voice synthesis, and a hacky but decently good solution to Kokoro's context window problem: breaking sentences into clauses. Also found out that 11labs is a lot more expensive than I thought. - Event context: January 29th - LA AI Tinkerers Meetup & Demos (w/ Special Guest Alibaba WAN) — 2026-01-30 — Los Angeles - Public talk page: https://la.aitinkerers.org/talks/rsvp_wigMst0JqyA ### [Building a vibe-coding community](https://hong-kong.aitinkerers.org/talks/rsvp_-fkHAQKFZ8o) We built websites with the help of AI to allow everyone to generate apps/games/art and share and learn such creations from one another on a social media platform. We've encountered various challenges along the way and will share our journey. - Event context: AI Tinkerers Hong Kong Meetup - October 22nd — 2025-10-22 — Hong Kong - Public talk page: https://hong-kong.aitinkerers.org/talks/rsvp_-fkHAQKFZ8o ### [Generating custom AI workflows](https://dublin.aitinkerers.org/talks/rsvp_03JUI-YtPrE) In this technical presentation I'll show how coso.ai leverages LLM's to to generate custom AI workflows. - Event context: AI Tinkerers Dublin Anniversary Meetup — September 10, 2025 — 2025-09-10 — Dublin - Public talk page: https://dublin.aitinkerers.org/talks/rsvp_03JUI-YtPrE ### [​Agentic understanding of large codebases](https://vancouver.aitinkerers.org/talks/rsvp_tvER5ildlm0) Sourcebot is the open source code intelligence platform. We're using flagship agents to help developers ask questions against large diverse codebases. - Event context: AI Tinkerers Vancouver - July 8th hosted by ScalePad — 2025-07-09 — Vancouver - Public talk page: https://vancouver.aitinkerers.org/talks/rsvp_tvER5ildlm0 ### [​Agentic understanding of large codebases](https://vancouver.aitinkerers.org/talks/rsvp_HMla5T2nXdc) Sourcebot is the open source code intelligence platform. We're using flagship agents to help developers ask questions against large diverse codebases. - Event context: AI Tinkerers Vancouver - July 8th hosted by ScalePad — 2025-07-09 — Vancouver - Public talk page: https://vancouver.aitinkerers.org/talks/rsvp_HMla5T2nXdc ## Related Technologies - [Next](https://aitinkerers.org/technologies/next) ([Markdown](https://aitinkerers.org/technologies/next.md)) — 186 public demos - [React](https://aitinkerers.org/technologies/react) ([Markdown](https://aitinkerers.org/technologies/react.md)) — 219 public demos - [Anthropic API](https://aitinkerers.org/technologies/anthropic-api) ([Markdown](https://aitinkerers.org/technologies/anthropic-api.md)) — 66 public demos - [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 214 public demos - [Claude Haiku](https://aitinkerers.org/technologies/claude-haiku) ([Markdown](https://aitinkerers.org/technologies/claude-haiku.md)) — 10 public demos - [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos - [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos - [TypeScript](https://aitinkerers.org/technologies/typescript) ([Markdown](https://aitinkerers.org/technologies/typescript.md)) — 205 public demos - [AWS](https://aitinkerers.org/technologies/aws) ([Markdown](https://aitinkerers.org/technologies/aws.md)) — 38 public demos - [Claude Opus](https://aitinkerers.org/technologies/claude-opus) ([Markdown](https://aitinkerers.org/technologies/claude-opus.md)) — 18 public demos - [ElevenLabs](https://aitinkerers.org/technologies/elevenlabs) ([Markdown](https://aitinkerers.org/technologies/elevenlabs.md)) — 42 public demos - [MCP](https://aitinkerers.org/technologies/mcp) ([Markdown](https://aitinkerers.org/technologies/mcp.md)) — 129 public demos - [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos - [OpenAI O3](https://aitinkerers.org/technologies/openai-o3) ([Markdown](https://aitinkerers.org/technologies/openai-o3.md)) — 2 public demos - [Streamlit](https://aitinkerers.org/technologies/streamlit) ([Markdown](https://aitinkerers.org/technologies/streamlit.md)) — 89 public demos - [Supabase](https://aitinkerers.org/technologies/supabase) ([Markdown](https://aitinkerers.org/technologies/supabase.md)) — 90 public demos - [Amazon EKS](https://aitinkerers.org/technologies/amazon-eks) ([Markdown](https://aitinkerers.org/technologies/amazon-eks.md)) — 3 public demos - [Apple Intelligence](https://aitinkerers.org/technologies/apple-intelligence) ([Markdown](https://aitinkerers.org/technologies/apple-intelligence.md)) — 2 public demos