AI agent news for August 12, 2026

4 stories · August 12, 2026 · ~4 min read

By the numbers#

Today's numbers at a glance

On the radar today#

💰 Sessions can be seeded with up to 50 initial events in the create call#

POST /v1/sessions now accepts initial_events carrying up to 50 user.message and user.define_outcome events. A non-empty list starts the agent loop in the same call, removing the separate send-events request.

The number: 50 (Maximum initial events accepted on session create). platform.claude.com

Why it matters: It also changes the status a client should expect: a seeded session is created directly in running and never passes through idle, so code waiting for that transition waits forever.

Source: Anthropic (Claude)

---

🧠 Gemini 3.6 Flash goes stable and sampling parameters are deprecated#

Google launched stable versions of Gemini 3.6 Flash and Gemini 3.5 Flash-Lite with improved token efficiency and cost-effectiveness, and deprecated the temperature, top_p and top_k sampling parameters.

The number: 3 (Sampling parameters deprecated (temperature, top_p, top_k)). ai.google.dev

Why it matters: Two major providers deprecated sampling parameters within weeks of each other. Steering output variety through temperature is ending as a cross-vendor technique, and prompting replaces it.

Source: Google Gemini

---

🧠 Legacy Workbench and the experimental prompt tools APIs retire on August 17#

The legacy Workbench is being sunset with access ending 2026-08-17. Saved prompts, variables and evals are not supported in the updated Workbench and must be exported. The experimental prompt tools APIs for generating, improving and templatizing prompts retire on the same date and will return an error afterwards.

The number: Aug 17, 2026 (Workbench and prompt tools API retirement date). platform.claude.com

Why it matters: There is an export step with a deadline attached, and three API endpoints that will start erroring. Both are easy to miss because neither breaks anything today.

Source: Anthropic (Claude)

---

🧠 Rate limits rise across the API and usage tiers consolidate to three#

Sonnet and Haiku rate limits now match Opus at every usage tier, and usage tiers have been consolidated into three: Start, Build and Scale. Most organizations move to a higher tier, no organization receives lower limits than before, and no action is required.

The number: 3 (Consolidated usage tiers (Start, Build, Scale)). platform.claude.com

Why it matters: Capacity planning built around the old five-tier ladder needs re-reading, and workloads previously throttled onto a cheaper model may no longer need to be.

Source: Anthropic (Claude)

+10 more on the radar today: see the full feed.

What I'd actually do about it#