GitHub launched computer use in public preview for Copilot CLI and its desktop app, letting agents operate macOS and Windows GUI applications by reading content and controlling windows. The preview debuted on Thursday. It uses a local MCP server and access permissions, but GitHub says developers should try APIs, MCP servers, terminal or browser tools first for more predictable results, while enterprise policies can block computer use.
Amazon Quick was paired with a deterministic rules engine in a new “Adjudicated Query” pattern to check large numbers of apartment leases against versioned landlord-tenant rules via chat plus a drillable dashboard.
The reference example targets a portfolio of 50,000 leases across multiple states.
As a result, compliance sweeps produce provable completeness receipts and defensible evidence chains, preventing model-based silent narrowing or skipped records while limiting AI calls to an exploratory clause-search path.
Claude Desktop on Amazon Bedrock was missing integrated web search, so it could only answer using knowledge up to the model’s training cutoff. The setup uses Web Search backed by an AWS web index spanning tens of billions of documents. The result is that Claude Desktop can securely retrieve current information via an Amazon Bedrock AgentCore Gateway with JWT-based authentication through AWS IAM Identity Center and Cognito.
Qarunbook launched to help users write and manage test plans with options to work through them themselves, with a team, or with AI over MCP. The free plan includes no card and offers 20,000 credits for Proactive AI for Mac. Fixed issues must be retested before they count as passed, changing how test results are tracked.
Banger launched an AI-powered email automation platform that combines journeys, campaigns, product emails, mailboxes, and reply handling in one place. The free plan starts with 100 emails per day. This lets users run email workflows from chat-based AI apps like ChatGPT or Claude and manage branded, tested, and translated email flows through a web app.
Mercury released Mercury Voice for general availability to enterprise customers, positioning it as a diffusion LLM tuned for low-latency voice agents. Mercury Voice returned its first answer token in under 320 ms median on real customer-service prompts. It targets a sub-500 ms time-to-first-answer budget for natural conversation while offering set pricing ($0.40/M input and $1.50/M output) and an OpenAI-compatible enterprise API endpoint.
Earendil released Pi 1.0, an open-source AI agent software package, and it reached the top spot on Hacker News with 1,000 points. The release adds Codemode with native Model Context Protocol support and other changes aimed at cost and workflow control. As a result, Pi is positioned as stable enough for business use and continues expanding alongside the experimental Pi Durable framework for long-running, crash-recovering multi-user agents.
Bevel launched eu/jev as the second launch from the company, offering a Jev-like System One model hosted in the EU for users blocked by GDPR and data sovereignty limits elsewhere. It runs on Hetzner GPUs in Germany and matches Jev’s pricing, with free output tokens. The result is a GDPR-compliant way to call a Jev-style model without storing prompts or answers.
Takweem AI launched an AI-first calendar that lets users schedule, reschedule, and protect focus using plain-language or voice requests. It starts with a free test that includes 20,000 credits. It integrates with Google Calendar now (with Outlook planned) and introduces approval and Undo so changes to other people’s schedules require confirmation.
Microsoft released MAI-Transcribe-2-Streaming along with two new text-to-speech models to help developers build faster, more natural voice agents with live transcription. MAI-Transcribe-2-Streaming costs 54 cents per audio hour and begins returning transcript hypotheses within 320 milliseconds on average. The update shifts voice-agent development toward streaming captions and earlier processing while letting builders trade off latency and cost via the separate transcription and speech models.
Every AI story that matters,
in your inbox by 8am.
TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the
day in two minutes. Follow companies and topics for alerts, or get the
briefing in Slack. Free, no spam, unsubscribe anytime.
Reading TLDRocket needs no cookies, and the readership counts we rely on come from
our own cookieless analytics. Google Analytics is the exception: it sets cookies and
reports to Google, so it stays switched off until you allow it. You can change your
mind any time from “Cookie settings” in the footer.
Strictly necessary
Session security and form protection (tldrocket-session,
XSRF-TOKEN, 2 hours). The site cannot work without them,
so they need no consent.
Always on
Google Analytics 4 (_ga,
_ga_<id>, up to 2 years). Measures which
stories and sections readers use. Google acts as a third-party processor and may
store the data outside the EU. No advertising, no profiling, no data sold.
