Enterprise Knowledge Search
Telstra's directors needed a faster way to find, search, and interrogate large volumes of board material, recall prior decisions, and verify whether management recommendations and requested actions were properly addressed before Board and Committee meetings.
Reported impact
The agent reduces friction in board preparation by helping directors find and interrogate relevant information more quickly, while maintaining strong governance, privacy, and security controls around highly sensitive board information.
Telstra built a Board AI agent inside its protected internal environment to help directors prepare for Board and Committee meetings using only approved internal materials. The agent provides a chat and prompt interface that lets directors search and interrogate previously supplied board content, summarise past papers or minutes on a topic, check earlier resolutions, and review whether requested actions have been addressed in current papers. Its retrieval scope is intentionally constrained to a walled garden containing Board and Committee papers and minutes, actions and resolutions, annual reports, released ASX announcements, and Group policies. Telstra says the system was developed through its Data and AI joint venture with Accenture, aligned to existing privacy, cybersecurity, and data-governance standards, isolated from public or external large language models, and extensively tested for risks such as hallucinations.
Board and Committee papers and minutes, actions and resolutions, annual reports, released ASX announcements, and Group policies are made available inside a constrained internal corpus. Directors query the Board AI agent through prompts and chat, and the agent returns summaries, prior decisions, and checks against current board papers within that walled garden.
"Because Board information is highly sensitive, the agent sits entirely within Telstra’s protected internal environment."
"It’s not connected to any public or external large language models, and it’s been extensively tested to manage known risks such as hallucinations."
"The Board AI agent operates within a deliberately constrained ‘walled garden’. It can only interrogate material that has already been provided to the Board, including past Board and Committee papers and minutes, actions and resolutions, annual reports, previously released ASX announcements and Group policies."
"They weren’t asking for more information ahead of a Board meeting – they were asking for help finding the right information, quickly, from the material they already had."
"Using simple prompts and chat, directors can ask the agent to summarise relevant past papers or minutes on a particular topic, check what resolutions were agreed previously, or see whether actions the Board asked for have been properly addressed in current papers."
"We’ve recently launched a Board AI agent to support our directors as they prepare for Board and Committee meetings."
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
In-house Sample Jul 23, 2026 Telefónica Telefónica needs to evolve and maintain a very large API and microservices estate without slowing delivery, while keeping integrations understandable, compliant, secure and maintainable; it also wants to reduce manual… AI agent · generative AI In-house Sample Mar 30, 2026 Telefónica Germany Telefónica's network operations teams had to handle growing network complexity, massive alarm volumes, and incident analysis workflows that made root-cause identification and troubleshooting slower and harder for NOC… Network Operation Agent (NOA) · database · ticketing system In-house Sample Sep 7, 2023 AT&T AT&T wanted to put generative AI into everyday employee workflows so software developers, engineers, finance teams, supply chain staff, HR, customer service, and fraud teams could work faster on code, data analysis,… in some cases 2x the speed, 1/2 the cost Ask AT&T · Falcon transformers · Meta LLaMA 2 