> ## Documentation Index > Fetch the complete documentation index at: https://docs.deepblocker.ai/llms.txt > Use this file to discover all available pages before exploring further. # What's new > Changes you can see in the console, on calls, in reports, in your account and on the public site, one entry per production release. Every production release carries a tag. Only releases with a change you can see are listed here. **10 November 2026** v2026.11.10-7 Research now reaches every calling system, so the caller knows who it claims to be and who it is calling on every pipeline. The campaign step has a new **Research used on this call** panel with two tick boxes, one for the caller and one for the person being called. Both are on by default and your choice is saved with the campaign. **10 November 2026** v2026.11.10-6 Background sound starts the moment the call connects on the ElevenLabs Agents calling system, instead of a few seconds in. **8 November 2026** v2026.11.08-12 In **Connect your agent**, **Check connection** now says how many test tools your agent can see. **8 November 2026** v2026.11.08-11 Agent Assurance: workspaces with self-service turned on connect their agent to our test tools themselves, from the agent's **Connection** tab. **8 November 2026** v2026.11.08-4 UK caller numbers dial through the UK route, so they show correctly on the phone. Numbers that were never set up were removed from the picker. **8 November 2026** v2026.11.08-3 Agent Assurance PDFs no longer show our internal cost. A long campaign is now graded run by run. **7 November 2026** v2026.11.07-21 Every Agent Assurance report now says how it was tested: the attacker strength, the budget and the grader used. **7 November 2026** v2026.11.07-20 Grading judges only the MUST NOT rules, even when MAY rules are listed alongside them. **7 November 2026** v2026.11.07-19 Agent Assurance: workspaces with self-service turned on sign the testing agreement in the console, plan tests, and start, pause and stop them. **7 November 2026** v2026.11.07-18 Agent Assurance: workspaces with self-service turned on add their own agents, prove the agent is theirs, and set its rules. **7 November 2026** v2026.11.07-16 Agent Assurance can now be run by the customer. It is off until DeepBlocker turns it on for your workspace; the console says so. **6 November 2026** v2026.11.06-33 The campaign edit card has a caller-number picker, so you can change the number without reopening the wizard. **6 November 2026** v2026.11.06-32 Pick a UK or US caller number per campaign, from the numbers allocated to your workspace, on the **From where and when** step. **6 November 2026** v2026.11.06-28 Agent Assurance reports with many matched tool calls publish again. Planted keys hidden in field names are now masked. **6 November 2026** v2026.11.06-27 The Agent Assurance card on the pricing page names only the channels that run today. **6 November 2026** v2026.11.06-26 The Agent Assurance page on deepblocker.ai explains what the latest proof run showed and which plan fits. **6 November 2026** v2026.11.06-25 Refreshing an Agent Assurance report drops any finding its test runs no longer support. **6 November 2026** v2026.11.06-23 The evidence card for a planted address says plainly when no key was sent. **6 November 2026** v2026.11.06-22 An agent that merely reached a planted web address is no longer reported as having sent a planted key. **6 November 2026** v2026.11.06-21 Cloned voices are only visible within the workspace that made them. The call language you set on the attacker is carried through to the voice. **6 November 2026** v2026.11.06-19 Activity logs sent from Claude Code with an encoded key are accepted. **6 November 2026** v2026.11.06-16 Agent Assurance tests replay published backdoor triggers and run an unusual-input sweep. **6 November 2026** v2026.11.06-15 An immediate campaign now waits for its calling hours, so nobody is called at night by accident. Tick **Call right now, even outside my hours** to dial straight away. **6 November 2026** v2026.11.06-14 Agent Assurance reports say how much power the agent holds, based on the tools it can reach. **6 November 2026** v2026.11.06-13 The first-run wizard is clearer about the department field, impersonation consent and the calling system. **6 November 2026** v2026.11.06-12 Coding agents can be tested with planted instructions hidden in files. **6 November 2026** v2026.11.06-11 A coding agent's own tools are read from the activity logs it sends, so findings name the real tool. **6 November 2026** v2026.11.06-8 Coding tool categories run through rules, grading, findings and the report. **6 November 2026** v2026.11.06-7 The sandbox offers fake command, file, web and package tools for testing coding agents. **6 November 2026** v2026.11.06-6 Traced calls from Claude Code get their real outcome in findings. **6 November 2026** v2026.11.06-4 Agent Assurance reports have a new section, where your model came from, on the model supply chain. **6 November 2026** v2026.11.06-3 The public site says which agent channels run today: web, API and Telegram. **6 November 2026** v2026.11.06-2 The Agent Assurance page on deepblocker.ai explains that a test measures the damage, whatever takes control of the agent. **5 November 2026** v2026.11.05-21 A report is produced automatically after every Agent Assurance test. On Essentials and Pro it publishes straight away; on other plans we review it first. **5 November 2026** v2026.11.05-20 The Agent Assurance overview shows your plan usage live. **5 November 2026** v2026.11.05-18 Agent Assurance plans are measured in test conversations. Usage shows as OK, Near limit or Used up. **5 November 2026** v2026.11.05-17 An agent's latest result comes from its latest published report. **5 November 2026** v2026.11.05-16 The Agent Assurance console is in tabs: Overview, Agents, Tests and Reports. **5 November 2026** v2026.11.05-13 The first-run welcome window was polished. **5 November 2026** v2026.11.05-12 Fixes to the **Get started** checklist, including the celebration when you finish it. **5 November 2026** v2026.11.05-11 A new workspace sees a short recommended list: two voices and three campaign scenarios to start from. **5 November 2026** v2026.11.05-8 A welcome window on your first visit, a **Get started** pill that stays in reach, and a celebration when the checklist is complete. **5 November 2026** v2026.11.05-7 Your first attacker can use a ready-made voice, so you can take a test call before cloning anything. **5 November 2026** v2026.11.05-5 The **Get started** checklist appears as soon as you sign in. **5 November 2026** v2026.11.05-4 A **Get started** checklist walks a new workspace through four steps to its first test call. **4 November 2026** v2026.11.04-28 Invite your team by email, see the members list, and use the redesigned Account settings and account dashboard. **4 November 2026** v2026.11.04-20 Longer office and street background sounds, so neither audibly loops during a call. **4 November 2026** v2026.11.04-18 A longer restaurant background sound, so it does not audibly loop. **4 November 2026** v2026.11.04-17 A clear **Out of red-team minutes** window shows your licence, the minutes left and the price of extra minutes. A new adaptive "CEO phone stolen" template. **4 November 2026** v2026.11.04-15 The line goes live the moment the person answers. The silent gap at the start of a call is gone. **4 November 2026** v2026.11.04-14 The trust page says exactly where data is processed. **4 November 2026** v2026.11.04-8 Agent Assurance reports show the attack engine's own judgement next to our grade. **4 November 2026** v2026.11.04-7 Your agent's own activity logs, sent over OpenTelemetry, become tool-call evidence in Agent Assurance reports. **3 November 2026** v2026.11.03-28 Newsletter sign-up on the homepage, **Newsletter** in the menu, and past issues readable online. **3 November 2026** v2026.11.03-24 A new deepblocker.ai homepage and pricing page. **3 November 2026** v2026.11.03-19 The newsletter confirmation link works without redirecting. **3 November 2026** v2026.11.03-13 Sign up to DeepFake Weekly by email. **3 November 2026** v2026.11.03-9 The UK site, uk.deepblocker.ai, shows the DeepBlocker design. **3 November 2026** v2026.11.03-7 More agent set-ups in **Connect your agent**. **2 November 2026** v2026.11.02-17 A **Connect your agent** panel for the hosted sandbox, with connection status. **2 November 2026** v2026.11.02-12 Declare your agent's own tools for an Agent Assurance test. **2 November 2026** v2026.11.02-9 Speech-to-text can run in Europe for a workspace. Ask us to set it for yours. **2 November 2026** v2026.11.02-7 Telegram tests produce a report. **2 November 2026** v2026.11.02-5 Cloned voices are deleted 30 days after they are made, and call transcripts and results 90 days after the call, automatically. **2 November 2026** v2026.11.02-4 The trust page states data residency the honest way: a UK or EU placement, not a promise for every customer. **30 October 2026** v2026.10.30-11 The rehearsal **Improve** action shows a plain message instead of raw error text. **30 October 2026** v2026.10.30-1 When the calling system is full, people are queued instead of marked failed. **How many at once** is capped at your plan limit. **29 October 2026** v2026.10.29-4 A test call starts one caller per session, even when you press **Call again**. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.