•1 min read•from InfoQ
Presentation: State of Play: AI Coding Assistants
Our take
In her presentation, "State of Play: AI Coding Assistants," Birgitta Böckeler explores the rapid evolution of AI agents, highlighting their transition from basic "vibe coding" to advanced context engineering. She addresses the importance of architectural constraints and "harness engineering" as essential safety nets for autonomous code generation. Böckeler provides key insights for leaders, emphasizing the need to balance speed with maintainability, security risks, and the financial implications of AI autonomy. This discussion is crucial for anyone navigating the future of coding in an AI-driven landscape.
Birgitta Böckeler discusses the rapid evolution of AI agents, moving beyond "vibe coding" to sophisticated context engineering. She explains how architectural constraints and "harness engineering" create the safety nets required for autonomous code generation. She shares vital insights for leaders on balancing speed with maintainability, security risks, and the cost of AI autonomy.
By Birgitta BöckelerRead on the original site
Open the publisher's page for the full experience
Related Articles
- Presentation: Agents, Architecture, & Amnesia: Becoming AI-Native Without Losing Our MindsTracy Bannon shares a cautionary tale of "The Sorcerer’s Apprentice" to illustrate the risks of unbridled AI autonomy. She discusses the shift from bots to autonomous agents, explaining how reckless speed leads to "Architectural Amnesia." She provides a concrete framework for "Minimum Viable Governance," focusing on identity, delegation, and ADRs to manage debt at machine speed across the SDLC. By Tracy Bannon
- Presentation: Choosing Your AI Copilot: Maximizing Developer ProductivitySepehr Khosravi discusses the current state of AI-assisted coding, moving beyond basic autocompletion to sophisticated agentic workflows. He explains the technical nuances of Cursor’s "Composer" and Claude Code’s research capabilities, providing tips for managing context windows and MCP integrations. He shares lessons from industry leaders on shrinking process time beyond just writing code. By Sepehr Khosravi
- Salesforce’s Agentforce Vibes 2.0 targets a hidden failure: context overload in AI agentsWhen startup fundraising platform VentureCrowd began deploying AI coding agents, they saw the same gains as other enterprises: they cut the front-end development cycle by 90% in some projects. However, it didn’t come easy or without a lot of trial and error. VentureCrowd’s first challenge revolved around data and context quality, since Diego Mogollon, chief product officer at VentureCrowd, told VentureBeat that “agents reason against whatever data they can access at runtime” and would then be confidently “wrong” because they’re only basing their knowledge on the context given to them. Their other roadblock, like many others, was messy data and unclear processes. Similar to context, Mogollon said coding agents would amplify bad data, so the company had to build a well-structured codebase first. “The challenges are rarely about the coding agents themselves; they are about everything around them,” said Mogollon. “It’s a context problem disguised as an AI problem, and it is the number one failure mode I see across agentic implementations.” Mogollon said VentureCrowd encountered several roadblocks in overhauling its software development. VentureCrowd's experience illustrates a broader issue in AI agent development. The models are not failing the agents; rather, they become overwhelmed by too much context and too many tools at once. Too much context This comes from a phenomenon called Context bloat, when AI systems accumulate more and more data, tools or instructions, the more complex the workflows become. The problem arises because agents need context to work better, but too much of it creates noise. And the more context an agent has to sift through, the more tokens it uses, the work slows down and the costs increase. One way to curb context bloat is through context engineering. Context engineering helps agents understand code changes or pull requests and align them with their tasks. However, context engineering often becomes an external task rather than built into the coding platforms enterprises use to build their agents. How coding agent providers respond VentureCrowd relied on one solution in particular to help it overcome the issues with context bloat plaguing its enterprise AI agent deployment: Salesforce’s Agentforce Vibes, a coding platform that lives within Salesforce and is available for all plans starting with the free one. Salesforce recently updated Agentforce Vibes to version 2.0, expanding support for third-party frameworks like ReAct. Most important for companies like VentureCrowd, Agentforce Vibes added Abilities and Skills, which they can use to direct agent behavior. “For context, our entire platform, frontend and backend, runs on the Salesforce ecosystem. So when Agentforce Vibes launched, it slotted naturally into an environment we already knew well,” Mogollon said. Salesforce’s approach doesn’t minimize the context agents use; rather, it helps enterprises ensure that context stays within their data models or codebases. Agentforce Vibes adds additional execution through the new Skills and Abilities feature. Abilities define what agents want to accomplish, and Skills are the tools they will use to get there. Other coding agent platforms manage context differently. For example, Claude Code and OpenAI’s Codex focus on autonomous execution, continuously reading files, running commands and as tasks evolve, expanding context. Claude Code has a context indicator that which compacts context when it becomes too large. With these different approaches, the consistent pattern is that most systems manage growing contexts for agents, not necessarily to limit them. Context keeps growing, especially as workflows become more complex, making it more difficult for enterprises to control costs, latency and reliability. Mogollon said his company chose Agentforce Vibes not only because a large portion of their data already lives on Salesforce, making it easier to integrate, but also because it would allow them to control more of the context they feed their agents. What builders should know There’s no single way to address context bloat, but the pattern is now clear: more context doesn't always mean better results. Along with investing in context engineering, enterprises have to experiment with the context constraint approach they are most comfortable with. For enterprises, that means the challenge isn’t just giving agents more information—it’s deciding what to leave out.
Tagged with
#natural language processing for spreadsheets#generative AI for data analysis#Excel alternatives for data analysis#AI formula generation techniques#financial modeling with spreadsheets#no-code spreadsheet solutions#rows.com#AI agents#context engineering#autonomous code generation#vibe coding#architectural constraints#AI autonomy#harness engineering#maintainability#security risks#safety nets#coding assistants#speed#evolution