BEGIN:VCALENDAR VERSION:2.0 PRODID:Events Booking BEGIN:VEVENT UID:6af4fd8d6961e SUMMARY:James Parham - Brand and Land: Agentic AI DESCRIPTION:  \; Presentation Title James Parham - Brand and L and: Agentic AI Presentation Speaker James Parham Presentation Abstr act Most project managers meet AI as a chat box. That confuses two diffe rent things: the large language model (LLM)\, which generates language\, a nd retrieval-augmented generation (RAG)\, which pulls your own documents i nto that generation so answers are grounded in your project\, not in whate ver the model remembers. You do not need to build or train an LLM. You nee d governance first\, then an agent that retrieves from knowledge you contr ol.In this one-hour session\, James Parham walks an at-risk portfolio-and- below scenario (Northbridge Care Group / Project Harbor) and shows how to use PMI Inputs\, Tools and Techniques\, and Outputs (ITTOs) and the Exam C ontent Outline as reference models to define recovery governance before an y AI runs. The room sees why a project can look green on throughput while Demand-to-Staff cannot name a staffable gate. He uses Tonic Fabricate to g enerate synthetic cost-of-nonconformance and delay data so the cost of dua l capacity truth\, open priority decisions\, and an unstaffed release gate is visible in numbers\, not only in narrative. Reference models give the structure\; the synthetic ledger makes the price of waiting concrete\; the team selects and adapts what applies. He then shows his own agentic syste m\, built around his own RAG over his standards and project materials\, ge nerating a recovery plan and information radiators (including teaching fre ehands and an A3 problem card) that stakeholders can read at a glance. The demo is not Claude or ChatGPT as the product. The point is owning the age nt and the retrieval layer while using known good models under the hood. P articipants leave able to separate LLM from RAG\, use PMI reference models plus quantified nonconformance and delay signals to shape governance\, an d sketch a governed starter pattern for their next at-risk initiative. & nbsp\; LOCATION:Virtual Event/Web Conference DTSTART:20270130T170000Z DTEND:20270130T180000Z DTSTAMP:20261112T050446Z ORGANIZER;CN=PMI California Inland Empire Chapter:MAILTO:info@pmicie.org END:VEVENT END:VCALENDAR