Author: admin

New research shows AI coding agents spend >80% of their time searching for files rather than editing them. Cielara Code changes this by using a clear map of production software. This approach helps find the right code to change faster, cheaper, and more accurately than typical coding agents.

San Francisco, CA – May 06: AI coding tools are now producing code faster than teams can check what it will do in real use.  Causal Dynamics Lab (CDL) announced new research explaining why this happens, along with a new product called Cielara Code. This product achieved the highest accuracy in code localization among AI coding tools, outperforming both Claude Code (Opus-4.6) and OpenAI Codex (GPT-5.4) across three independent tests.

CDL studied how coding agents operate by tracking their actions across thousands of coding sessions. They found 56.8% of agents’ actions involved reading files, and 24.2% involved using grep. Less than 1% of their actions were actual code edits. The problem was not that agents couldn’t write code; they had difficulty finding the correct code to edit. The situation worsened with more complex tasks: when a correct fix involved more than six files, the agents’ ability to recall the necessary information dropped significantly, and the computing power used in failed attempts increased by a factor of 4 compared to successful ones.

“Every coding agent out there today uses grep, which is like a surgeon operating without imaging,” said Hasibul Haque, CEO at Causal Dynamics Lab. “We created Cielara Code to help agents see better: it provides a clear understanding of the working environment, making the reasons behind each change clear and verifiable.”

The 2025 DORA report showed the use of AI coding tools led to a 7.2% drop in deployment stability. AWS CTO Werner Vogels called this problem “dynamic verification debt.” A well-known issue with Claude Code (GitHub issue #42796) illustrates the same problem on a larger scale: current agents treat code as flat text without showing how files connect, how functions call each other, or how changes affect the overall system.

How Cielara Code works

Cielara Code uses a model to represent a customer’s production environment in a 6-layer causal graph. This graph includes information on what the code does, why it was created, who owns it, its limitations, where it runs, and what happens at runtime. If there is a failure, it can be linked back to the specific code change, the developer who approved it, and the reason for that change. Before an agent begins to explore, Cielara Code builds a Code Dependency Causal Graph. This graph tracks four types of relationships, allowing the agent to navigate the structure rather than just look through files one by one.

Benchmark results

Across three independent benchmarks, Cielara Code beat both Claude Code (Opus-4.6) and OpenAI Codex (GPT-5.4) at the hardest part of agent work: finding the right place to make a change. Overall localization accuracy hit 0.774, versus 0.738 for Claude Code and 0.707 for Codex. On MULocBench (1,033 issues across 46 repositories), Cielara reached 0.752 recall@5 versus 0.727 for Claude Code, and cut mean task time from 141.84 to 128.62 seconds. The result: fewer wrong-file edits, fewer failed runs, and 30 to 40 percent lower compute cost per task.

REASONARA: causal memory at enterprise scale

Cielara Code makes this practical through REASONARA, a graph-structured causal memory layer that stores 125M+ tokens of effective context but retrieves only what matters for each query. A typical lookup uses 1,000–2,500 tokens, compared with 23,000–115,000 for full-context approaches — a reduction of up to 98%. On independent benchmarks, REASONARA scores 94% on UltraDomain, 92% on LoCoMo, 73% on LoCoMo-plus, and 87.4% on LongMemEval, and runs 5–8× faster than Codex high-reasoning mode. The roadmap targets a one-billion-token context window.

Cielara Code is a safety layer for AI coding agents. It aims to enhance the safety of their output rather than replace them. Currently, 11 Fortune 100 and over 40 Fortune 500 companies use Cielara Code on their codebase.

“Board members and auditors expect more proactive risk management. Leaders now want proof that security can anticipate risks caused by fast-moving AI and automation, instead of just reacting after incidents,” said the CISO of one of the largest law firms in the United States, who is also a Cielara Code customer.

Phillip Miller, Vice President, Global Chief Information Security Officer, H&R Block added: “Enterprises need solutions to problems they cannot solve with people alone. Cielera’s technology is a generational leap towards the original promise of AI: tackling complexity 7×24 with acquired knowledge, deep reasoning, and unbeatable accuracy. For engineering teams, this means a single engine to discover faults in real-world deployments (including legacy, cloud) and provide clear resolution steps. When I wrote, Hacking Success, I described a world where AI needs strong, directive policy (not rules / guardrails) to be safe and effective. Information Security lags behind the innovation curve, as most options rely on legacy thinking including posture, gateways, and logging. Enterprises now have an option to leverage Cielera’s models to oversee deployments of AI agents, models, and their supporting infrastructure.”

The team

The team has strong skills based on the problem they are addressing. CEO Hasibul Haque led platform engineering at Uber during its rapid growth. CTO Ryan Turner was a Staff Engineer at Uber and helped maintain the SPIRE Project within the Cloud Native Computing Foundation (CNCF). R&D is led by Dr. Xuchao Zhang, who worked at Microsoft Research, and Dr. Liang Zhao from Emory University, who has 200+publications and is ranked among the top 2% of scientists by Stanford University. CDL has a formal research partnership with Emory’s AI Lab.

“AI has already changed how people find information. The next step is to change how people make decisions by exploring possibilities, comparing options, and understanding the outcomes before making a choice,” said Matt Fisher, former Co-Founder and CTO of Daydream and an Adjunct Professor at Brown University. “That shift towards exploring outcomes is what CDL is focusing on.”

What’s next

The Production World Model serves as a foundation. Cielara Code and REASONARA are the first products to use this foundation. In the future, Causal Dynamics Lab will fully simulate the effects of changes in code, infrastructure, policy, and operation. This will create a permanent reasoning layer in the enterprise system that any AI agent can access before making changes that affect production.

Taipei, Taiwan — May 6, 2026 Synology today officially introduces AI Advisor, an intelligent assistant designed to simplify information discovery. By delivering accurate, localized technical guidance directly on Synology’s website, the AI Advisor ensures reliable insights while significantly reducing resolution time for users worldwide.

“AI Advisor integrates over a decade of Synology’s AI expertise,” said Steven Liang, Manager of the Generative AI Application Group at Synology. “With an agent-as-tool design, dynamic knowledge injection, context optimization, and a continuous evaluation pipeline, AI Advisor delivers accurate, high-quality responses and continuously refines itself. These innovations will extend across Synology product lineup, advancing our vision of secure, intuitive solutions.

Self-hosted ecosystem to ensure AI sovereignty

Prioritizing customer privacy, the AI Advisor utilizes a self-hosted LLM that operates entirely independent of third-party AI providers, ensuring no context is shared externally. Moving toward complete data sovereignty, the service will transition to a dedicated Synology infrastructure later in 2026, guaranteeing 100% data residency and keeping all user interactions within a secure, sovereign ecosystem.

Streamlined navigation from inquiry to implementation

AI Advisor integrates with Synology’s NAS Selector and NVR Selector tools. Users are guided through preliminary sizing and product recommendation workflows tailored to their deployment needs, enabling faster and more informed early-stage purchasing decisions. By understanding the intent and context of each query, the Advisor further streamlines the journey by directing users to relevant support articles, downloads, or configuration guides to ensure a fast transition from question to solution.

Accessibility and Availability

Alongside the introduction of AI Advisor, this website update brings support for global web accessibility standards, ensuring an inclusive and user-friendly experience for audiences worldwide.

The Synology Website AI Advisor is available now on Synology’s official website. To learn more about Synology’s AI-driven services and experience the new Advisor, visit Synology’s official website. www.synology.com

DETROIT, Mich. (May 5, 2026) — ITS America Conference & Expo, organized in partnership by RX Global and ITS America, introduces an expanded demonstration program for the 2026 ITS America Conference & Expo, taking place June 9-11 in Detroit, Michigan. Attendees will see firsthand how the newest technologies installed along roadways and within vehicles are making transportation in Detroit safer and more efficient. The program marks a significant leap beyond traditional outdoor demonstrations, delivering hands-on, immersive experiences that connect attendees with the latest intelligent transportation technologies in real-world conditions.

The Michigan Department of Transportation (Michigan DOT) is spearheading the ITS America Conference & Expo’s outdoor demonstration experiences, sponsored by Integral Blue, under the theme “Everyday Interoperability,” showcasing how everyday people benefit from a seamless ecosystem of emerging technologies. The 2026 program features a record number of demonstration participants, a milestone that reflects growing industry momentum and commitment to advancing intelligent transportation solutions.

“Michigan Department of Transportation is proud to showcase the State of Michigan as a living laboratory for next‑generation transportation,” said Michele Mueller, Manager Connected, Automated, Electrification at the Michigan Department of Transportation. “By demonstrating emerging innovations in active corridors, we provide the ITS community with a rare opportunity to experience how integrated, data-driven mobility solutions are shaping a safer, smarter, and more efficient mobility ecosystem.”

What makes this year’s ITS America Conference & Expo’s demonstration program truly distinctive is that attendees will experience the technology in transit to see how it works in real time. 

• The I-94 Freeway Experience spans a 45-mile route between downtown Detroit and Ann Arbor, featuring work zone warnings, road hazard alerts, and emergency vehicle applications delivered through advanced roadside sensors, dedicated communication units, and vehicle-to-network (V2N) cellular connectivity. 

• The M-1 Intelligent Woodward Experience runs four miles along 31 vehicle-to-everything (V2X)-equipped intersections between Huntington Place and the Electreon Inductive Charging Tour at the Henry Ford Health Center, deploying autonomous vehicle (AV) shuttles to demonstrate intersection-based mobility and safety services. 

• The Everyday Downtown Experience extends V2N applications throughout downtown Detroit, connecting AV shuttles, pedestrians, and micromobility users through a dedicated smartphone app that functions as a personal on-board unit for collision avoidance and vulnerable road user alerts.

• Anchoring the broader program is ITS America Conference & Expo’s Emergency Response Tech & Demo Day, scheduled for Thursday, June 11, from 10 a.m. to 6:30 p.m. in the Outdoor Demonstration Area. Brought to life by GFT Infrastructure Inc. and Michigan DOT, this immersive event spotlights infrastructure-based V2X communications for incident scene warnings, drone delivery integration for emergency operations, and an autonomous freight vehicle available for up-close technical exploration. Attendees will engage directly with practitioners and technology specialists throughout the day.

The Outdoor Demonstration Area, located directly outside Huntington Place’s Hall B entrance, features live product demonstrations from leading industry innovators including Brandmotion, showcasing its SmartHUD Digital Vehicle Alert System; Haas Alert, demonstrating networked V2X safety solutions; Integrity Security Services LLC; Miovision Technologies, presenting connected vehicle capabilities; PrePass Safety Alliance; and Ver-mac. Each company will give attendees direct access to hands-on evaluation of new solutions and one-on-one time with the experts driving these developments.

The expanded program includes curated small-group visits to Newlab, Detroit’s premier innovation center, where startups and emerging technologies are advancing the future of mobility. Attendees will also tour The Detroit Smart Parking Lab (DSPL), where live demonstrations from participating companies highlight EV charging, autonomous systems, robotics, and drone operations. An ADASTEC autonomous shuttle will transport attendees between event venues, the Smart Parking Lab, and Newlab. Tours run multiple times throughout the event and are limited to 15 participants per session. More information about demonstrations will be added to the website in the coming weeks.

“The demonstration experience program is what makes this event so distinct, and this year, we can truly say we are doing something new,” said Laura Chace, President and CEO of the Intelligent Transportation Society of America. “With a record number of demo participants and a reimagined experiential program, attendees will engage with technologies not just on the show floor, but out in the real world where they are making impact in our transportation systems.”

The demonstration program is sponsored by Integral Blue and powered by Michigan DOT. For more information on demonstrations and the full event experience, visit www.itsamericaevents.com/expo/en-us/discover/experiences.html

CiteSentinel Helps Lawyers File Faster While Avoiding Sanctions and Embarrassment

LOS ANGELES, May 5, 2026 — Legal tech startup BrentWorks Inc. launched CiteSentinel, among the first dedicated platforms built specifically to detect and prevent AI hallucinations in legal citations. The tool scans legal documents and flags case law, statutes, and legal authorities that may be fabricated, misstated, or otherwise erroneous, before they reach a judge.

Courts across the country are increasingly sanctioning attorneys who submit briefs containing invented case citations, a well-documented byproduct of generative AI drafting tools that produce authoritative-sounding, but entirely fictional, legal authority. CiteSentinel was designed to close that verification gap, giving attorneys a fast and easy way to confirm that every citation in a filing corresponds to a real case, a real statute, and a real legal authority.

“The legal profession is learning, in very public ways, that AI doesn’t just make mistakes, it confidently lies to your face,” said BrentWorks co-founder Brent Britton. “CiteSentinel is about restoring trust. It lets lawyers move fast with the irresistible efficiencies of generative AI while still filing documents reciting authorities they can stand behind. It also enables them to scan opposing counsel’s documents, giving them a competitive edge in the courtroom.”

Many attorneys who do not personally use AI to draft documents are discovering they have a problem anyway. Opposing counsel may have used AI. Co-counsel may have. Contract attorneys and paralegals almost certainly have access to it and may be using it

without disclosing that fact. When a brief containing fabricated citations reaches the court, the question of who drafted it quickly becomes secondary to the question of whose name is on it.

CiteSentinel lets attorneys scan any document, their own, a colleague’s, or an adversary’s, for citation errors before those errors become their problem. Attorneys who review opposing counsel’s filings with CiteSentinel gain an additional advantage: the ability to identify and challenge citations to authorities that simply do not exist.

Today, a lawyer’s supervisory obligation includes a question that would have seemed absurd just a few short years ago: Are the cases cited in this brief real or imaginary?

Senior lawyers cannot personally verify every citation in every document produced by everyone under their supervision. CiteSentinel can. At a cost that is modest compared to a single sanctions proceeding or the reputational damage that comes with public embarrassment before a court, CiteSentinel is among the most cost-effective risk management tools available to any law firm, legal department, or solo practice today.

Unlike traditional research platforms that focus on finding more information, CiteSentinel focuses on confirming the law cited in a document is real. Attorneys can scan:

· Their own AI-assisted drafts, before filing

· Submissions from co-counsel, contract attorneys, and support staff

· Opposing counsel’s filings, for strategic advantage

· Any document where citation accuracy carries professional or ethical weight

Like a reality check for legal briefs, the tool flags citations that may be hallucinated, misstated, or inaccurately referenced, allowing lawyers to correct errors before courts, clients, or competitors discover them first.

Under mounting deadline pressure, many attorneys now rely on AI-generated research, but verification has not kept pace. CiteSentinel addresses that verification gap head-on, helping lawyers practice faster, more accurately, and with the confidence that their work reflects reality.

BrentWorks was founded by Brent Britton, a veteran technology attorney and MIT-trained engineer, and Brent Hunter, a longtime technologist and AI pioneer. CiteSentinel is the first in a series of products the company will be releasing to elevate the practice of law in the age of AI.

BRENT C.J. BRITTON/CEO

Brent Britton is what happens when law school meets the MIT Media Lab. A veteran engineer, technology attorney licensed in three states (California, New York and Florida), and entrepreneur who literally wrote the book on IP law, Britton has spent his career guiding creators and companies at the frontier of innovation, overseeing billions of dollars of aggregate deal flow in the process. The culmination of his life is re-engineering legal tools to think faster, decide better, and serve humanity at the speed of innovation.

BRENT N. HUNTER/PRESIDENT AND CIO

Brent N. Hunter is a technology pioneer who applied neural networks to finance in 1993. He has since led multimillion-dollar transformation programs for Fortune 500 giants, including GE, Wells Fargo, Disney, and Warner Bros. Discovery. An author, technologist, and systems thinker, he fuses psychology, technology, and leadership into a single mission: to build intelligent systems that serve humanity.