I enjoyed this blog post on agents. Some historical context is always great. It argues that we have much better reasoning engines with LLMs, and by building engineering around them, we can also make agentic workflows more reliable. https://lnkd.in/dBFBS9zM
Jo Kristian Bergum’s Post
More Relevant Posts
-
Dive into the future of AI-driven data management with The Graphite Lab's innovative ID Mapping tool, part of the TGL Toolbox. This video provides a comprehensive guide on how to streamline your data operations using our advanced AI and automation technology. Whether you're looking to enhance data accuracy, speed up your workflows, or integrate complex data systems, ID Mapping is your go-to solution. #AI #idmapping #automation #zapier #shorts https://lnkd.in/eCyEZeJ4
ID Mapping in the TGL Toolbox
https://www.youtube.com/
To view or add a comment, sign in
-
Another impressive update from D5 Render - https://lnkd.in/eZGgQZuC D5 Render is a great real visualization tool, go check it out!
D5 Render 2.8 | AI Enhancer, Semi-transparent Effect, Sunlight Caustics, Vectorworks&Rhino LiveSync
https://www.youtube.com/
To view or add a comment, sign in
-
Crafting Intelligence: A Guide to Prompt Engineering https://lnkd.in/eAhqEbJ3
Crafting Intelligence: A Guide to Prompt Engineering
rickabbottfpd.substack.com
To view or add a comment, sign in
-
🥇 Optimizing LLMs with RAG: Key Technologies and Best Practices 🥇 https://hubs.li/Q02yzv1L0 Register now for the live online event on 29 May https://hubs.li/Q02yzv1L0 #LLM #RAG
Webinar: Optimizing LLMs with RAG: Key Technologies and Best Practices
poolparty.biz
To view or add a comment, sign in
-
I'm exploring the idea of visually modelling the benefits of incorporating process improvements in legal service delivery. Using Claude, I built a little game this morning to serve as a baseline. Watch, try and remix at your pleasure. (Desktop only - not designed for mobile) The baseline is a lawyer accomplishing a randomized set of tasks to deliver on a client objective. Speed and completeness gets the lawyer a reputation bonus, delivery gaps and billing substantially above quote result in a reputation penalty. Bonus and penalties expressed in dollars, with impact on business expressed in the aggregate and not impacting the $$ and hours billed to the original client. I think if I treat a few of the tasks as being amenable to improvement (whether to a different person in the firm, document automation, AI or otherwise), I could represent them in the model through a time reduction. The impact of the time reduction would be an increased probability of getting the reputation bonus for early completion and decreased probability or extent of reputation damage through incomplete or above-quote work. https://lnkd.in/eJ3G_xXw
To view or add a comment, sign in
-
Delighted to share that I have successfully completed an amazing short course on AutoGen. 🚀 AutoGen enables building next-gen LLM applications based on multi-agent conversations with minimal effort. It simplifies the orchestration, automation, and optimization of a complex LLM workflow. Here's my perspective on one of the many applications of agentic design patterns in the financial services industry: an autonomous equity research analysis workflow. ✅ Equity research analyst asks copilot to generate research report on a company or a sector ✅ User proxy agent gives the instructions to planner ✅ Planner agent creates a plan to invoke multiple conversable agents in specific order ✅ Engineer agent writes code to gather real-time market and news data combined with proprietary data ✅ Executor agent runs the code and auto tweaks for performance ✅ Writer agent consumes the quant data from executor and creates a report including investment thesis, financial projections, valuations, potential risks and catalysts ✅ Risk and compliance monitoring agent provide feedback to the writer agent from regulatory lens ✅ Writer agent adjusts the report ✅ Human in the loop to review and confirm the final report Cut the cycle time from days to minutes. 💹 https://lnkd.in/e3Q5QC3c #AutoGen #MicrosoftResearch
Suresh Sethuramaswamy, congratulations on completing AI Agentic Design Patterns with AutoGen!
learn.deeplearning.ai
To view or add a comment, sign in
-
✅ Generate evaluation datasets in 5 minutes. ✅ Evaluate agent quality without waiting for subject matter experts to label data ✅ Quickly identify and fix low-quality outputs. Getting evals right is the first step to building a working, production agent system. We help to automate the *building* of evals!
Streamline AI Agent Evaluation with New Synthetic Data Capabilities
databricks.com
To view or add a comment, sign in
-
Selecting the right RAG (Retrieval-Augmented Generation) architecture depends primarily on the specific use case and implementation requirements, ensuring the system aligns with task demands. Agentic RAG is set to grow in importance, aligning with the concept of Agentic X, where agentic abilities are embedded within personal assistants, workflows, and processes. Here, the “X” represents the boundless adaptability of agentic systems, enabling seamless task automation and informed decision-making across diverse contexts for enhanced organisational efficiency and autonomy. Synthesising diverse document sources is crucial for addressing complex, multi-part queries effectively.
Four Levels of RAG — Research from Microsoft
cobusgreyling.medium.com
To view or add a comment, sign in
-
Did you know...it only takes a couple of clicks to get help with solving your tickets: ✅ Suggested solutions ✅ A list of clarifying questions to ask ✅ Diagnostic steps to take Imagine how much time your team can save every week. Check out more AI-driven features for service desk agents here: https://bit.ly/3Vw8Qbg
AI-powered service management solutions - Hornbill
hornbill.com
To view or add a comment, sign in
-
Excited to share my latest video: "Tree of Thoughts (TOT) Prompt Engineering: Advanced Prompting Techniques!!" In this video, Explore the powerful Tree of Thoughts (TOT) method and its advanced techniques for better AI prompts. Watch here: https://lnkd.in/gm358Mm2 Don't forget to like, comment, and share! Subscribe for more AI insights. #AI #PromptEngineering #TreeOfThoughts #TOT #AdvancedTechniques
Tree of Thoughts (TOT) Prompt Engineering: Advanced Prompting Techniques!!
https://www.youtube.com/
To view or add a comment, sign in
Chief Scientist at Vespa.ai
1moI also think it ties to ICL, guiding and improving each state transition (action) by examples https://blog.vespa.ai/vespa-in-context-learning/