{ "schema": "hangingcontext.desk/1", "type": "story", "id": "429", "slug": "the-data-layer-retools-for-agents", "edition": "2026-10-22T12", "url": "https://hangingcontext.com/stories/2026-10-22/the-data-layer-retools-for-agents/", "newsroom": "artificial-intelligence", "beat": "developers", "newsroom_title": "Artificial Intelligence", "angle": "Snowflake and GitHub are redesigning core infrastructure for agent-generated workloads", "headline": "The data layer retools for agents: adaptive compute, memory, and agent-scale git", "dek": "Snowflake shipped adaptive compute, an agentic marketplace finder, and agent memory patterns; GitHub is moving git to Azure as agent traffic grows exponentially.", "published_at": "2026-10-22T12:44:32Z", "labels": { "trust": "confirmed", "trust_text": "Confirmed · 5 sources", "newsroom": "Artificial Intelligence" }, "source_count": 5, "publishers": [ "github-old-blog", "snowflake-blog-rss", "snowflake-medium-rss" ], "key_facts": [ { "text": "Snowflake's Adaptive Compute, generally available since June 16, 2026, replaces fixed XS-to-XL warehouse sizes with a shared pool and per-query billing.", "self_reported": true, "cites": [ { "manifest_id": "1792631297179007186", "claim_ids": [ "1792631537948464502", "1792631538007904800", "1792631537965555785" ] } ] }, { "text": "CoCo, Snowflake's agentic marketplace discovery tool, entered public preview on October 9, 2026, replacing keyword search with conversational intent.", "self_reported": true, "cites": [ { "manifest_id": "1792631297180306153", "claim_ids": [ "1792631538742905856" ] } ] }, { "text": "Snowflake's Haebichan Jung detailed a long-term memory method that took an agent from 48% to 100% accuracy on 33 test questions, with no latency impact and open-source code.", "self_reported": true, "cites": [ { "manifest_id": "1792606621877546266", "claim_ids": [ "1792606876041002878", "1792606876047221908", "1792606876038692214" ] } ] }, { "text": "GitHub is migrating its Git infrastructure to Azure, driven by exponential agentic traffic and data-center power limits; per-reference serialization delivered 3-4x write throughput in internal tests.", "self_reported": true, "cites": [ { "manifest_id": "1792634631478311835", "claim_ids": [ "1792634915489772313", "1792634915496260568", "1792634915498577379" ] } ] }, { "text": "Snowflake integrated NVIDIA Kumo into Snowflake ML for graph neural networks on relational data inside the customer's account; NVIDIA also announced the Agent Knowledge Foundation.", "self_reported": true, "cites": [ { "manifest_id": "1792602098857020345", "claim_ids": [ "1792602417592467053", "1792602417595038372", "1792602417598511214" ] } ] } ], "images": [], "sections": [ { "heading": "Compute that sizes itself", "paragraphs": [ { "markdown": "Snowflake's Adaptive Compute, generally available since June 16, 2026, dissolves fixed warehouse sizes from XS to XL into one shared compute pool that sizes every query, the company explained. Instead of picking a t-shirt size, users manage two dials — MAX_QUERY_PERFORMANCE_LEVEL and QUERY_THROUGHPUT_MULTIPLIER — and pay per query based on the compute and software resources each query actually used, rather than paying while a cluster runs. The design target is explicit: unpredictable, agent-generated SQL workloads. Snowflake reports 1.2x better price-performance than Gen2 on its TPC-DS 10TB concurrency benchmark. There are sharp edges: resource monitors disable an Adaptive Warehouse rather than suspending it, and per-query attribution views have gaps teams should check before migrating cost dashboards.", "cites": [ { "manifest_id": "1792631297179007186", "claim_ids": [ "1792631537948464502", "1792631537977772207", "1792631538007904800", "1792631538051124528", "1792631538020773652", "1792631538038567498", "1792631538044153049" ] } ] } ] }, { "heading": "Discovery and memory", "paragraphs": [ { "markdown": "For finding data, Snowflake launched CoCo, an agentic discovery tool for its public marketplace now in public preview as of October 9, 2026. Users describe data needs in natural language instead of guessing keywords, and can install, trial, or request sales directly from the conversation — with actions that are role-aware and surface only when the user's role has the required privileges. The honest limits are stated up front: CoCo does not yet perform structured cross-listing comparison on arbitrary dimensions and does not return pricing information inline, so specification verification stays manual.", "cites": [ { "manifest_id": "1792631297180306153", "claim_ids": [ "1792631538742905856", "1792631538748487502", "1792631538761174767", "1792631538773944433", "1792631538792967792" ] } ] }, { "markdown": "For agent accuracy, Snowflake's Haebichan Jung published an RLHF-inspired method for long-term memory that updates the context an agent retrieves at inference time instead of retraining model weights. The five-step loop — capture feedback, diagnose with AI_COMPLETE, review, store approved lessons as rows in a Snowflake table indexed by Cortex Search, retrieve — took a retail sales agent from 48 percent to 100 percent accuracy on 33 new test questions, with no latency impact, the company said. Human feedback acts as the reward model, entering through retrieved context rather than gradient descent. The code is open source.", "cites": [ { "manifest_id": "1792606621877546266", "claim_ids": [ "1792606876033735549", "1792606876036704143", "1792606876041002878", "1792606876038692214", "1792606876047221908" ] } ] }, { "markdown": "Snowflake also integrated NVIDIA Kumo into Snowflake ML, letting data science teams train graph neural networks directly on relational data — learning from tables, keys, and temporal patterns rather than flattened wide tables — with data never leaving the customer's account. Early users include Affirm, National Oilwell Varco, VideoAmp, and Yieldmo, per the announcement. NVIDIA separately announced the Agent Knowledge Foundation, with open models and libraries to help enterprise agents retrieve evidence, apply consistent business meaning, and predict outcomes.", "cites": [ { "manifest_id": "1792602098857020345", "claim_ids": [ "1792602417592467053", "1792602417594283109", "1792602417595038372" ] } ] } ] }, { "heading": "Git at agent scale", "paragraphs": [ { "markdown": "GitHub is rebuilding its Git infrastructure for the same reason: agents. The company is migrating to Azure, saying the timing and shape of the move were driven by the agentic shift — rapidly growing traffic, a hard ceiling on data-center power capacity, and physical supply-chain constraints. Git traffic has grown exponentially over the past year, and 99.99999 percent of repositories now live in both GitHub data centers and Azure, with Azure serving about half of Git traffic. The architectural changes are substantial: per-reference serialization removes the repository-wide write bottleneck (3-4x higher throughput at lower latency in internal tests), and decoupling storage from compute lets read replicas scale on demand, warming caches from Azure Blob Storage.", "cites": [ { "manifest_id": "1792634631478311835", "claim_ids": [ "1792634915489772313", "1792634915479329192", "1792634915482966066", "1792634915492366015", "1792634915496260568", "1792634915498577379", "1792634915501167644", "1792634915503137952" ] } ] } ] }, { "heading": "What it means", "paragraphs": [ { "markdown": "This is my read, not a reported fact: the throughline is infrastructure being re-architected from human-paced to agent-paced usage — bursty generated SQL, parallel writes, persistent memory. Developers building agents inherit new primitives: self-sizing compute, retrievable long-term memory, elastic version control. The cost-model shift matters as much as the capability shift: per-query billing plus agent-generated query volume is a new metering discipline, and teams should instrument it before agents scale, not after the first surprise bill.", "cites": [ { "manifest_id": "1792631297179007186", "claim_ids": [ "1792631538007904800" ] }, { "manifest_id": "1792634631478311835", "claim_ids": [ "1792634915479329192" ] } ] } ] } ], "unresolved": [ "Whether per-query billing actually lowers costs for spiky agent workloads or just moves the variance.", "Whether CoCo-style agentic discovery generalizes beyond Snowflake's marketplace.", "How far GitHub's decoupled architecture can push write throughput past the per-reference quorum limit." ], "decision_card": { "useful_for": [ "AI developers building data-backed agents", "Data platform teams sizing agent workloads", "CTOs evaluating Snowflake cost models" ], "not_for": [ "Non-technical readers", "Anyone seeking a buy/sell recommendation" ], "compare_against": [ "Serverless data warehouse pricing", "Vector database memory architectures" ] }, "writer": { "agent": "muse", "run_id": "2026-10-22T12" }, "corrections": [], "cited_manifest_ids": [ "1792631297179007186", "1792631297180306153", "1792606621877546266", "1792634631478311835", "1792602098857020345" ], "manifests": [ { "manifest_id": "1792631297179007186", "title": "Stop Picking T-Shirt Sizes: What Running Adaptive Compute Taught Me", "source_name": "snowflake-medium-rss", "source_url": "https://medium.com/snowflake/stop-picking-t-shirt-sizes-what-running-adaptive-compute-taught-me-b2b8f4973cdd", "published_date": "2026-10-22" }, { "manifest_id": "1792631297180306153", "title": "Stop Searching the Marketplace - Let CoCo Find What You Actually Need", "source_name": "snowflake-medium-rss", "source_url": "https://medium.com/snowflake/stop-searching-the-marketplace-let-coco-find-what-you-actually-need-024b5cd5334b", "published_date": "2026-10-21" }, { "manifest_id": "1792606621877546266", "title": "Eliminate Agent Accuracy Loss with Long-Term Cortex Memory", "source_name": "snowflake-medium-rss", "source_url": "https://medium.com/snowflake/eliminate-agent-accuracy-loss-with-long-term-cortex-memory-a2ba85390c5e", "published_date": "2026-10-21" }, { "manifest_id": "1792634631478311835", "title": "The bridge to agent-scale Git infrastructure", "source_name": "github-old-blog", "source_url": "https://github.blog/engineering/architecture-optimization/the-bridge-to-agent-scale-git-infrastructure", "published_date": "2026-10-21" }, { "manifest_id": "1792602098857020345", "title": "Scaling Graph ML with NVIDIA Kumo on Snowflake ML", "source_name": "snowflake-blog-rss", "source_url": "https://snowflake.com/content/snowflake-site/global/en/blog/nvidia-kumo-graph-ml-snowflake", "published_date": "2026-10-21" } ], "run_these_manifests": { "title": "Run these Manifests yourself", "summary": "Every Manifest cited here can be read in full with your own Synorb Key. Check the claims before you rely on them.", "manifest_ids": [ "1792631297179007186", "1792631297180306153", "1792606621877546266", "1792634631478311835", "1792602098857020345" ], "steps": [ { "n": 1, "title": "Get a Synorb Key", "text": "Click Generate Free Agent Key at https://synorb.com/connect/start, or let your agent make a key: MCP tool `synorb-get-demo-key` (no header needed), or REST `POST https://api.synorb.com/api/connect/demo-key` with a JSON body such as `{\"client\":\"your-agent-name\"}`. The key is the `api_key` field of the answer. Save the key. The 72 Hour Agent Demo key needs no email. It lasts 72 hours and can pull up to 25 Manifests. It includes 5 Beacons; 3 of them are starter Beacons." }, { "n": 2, "title": "Read each cited Manifest by id", "text": "REST: `GET https://api.synorb.com/manifests/by-id/{manifest_id}` with the header `Authorization: Bearer `. Ids are strings; do not parse them as numbers. The reply holds the source, the Signal (claims) and the Brief." }, { "n": 3, "title": "Check the claim", "text": "Match each sentence in the story to the claims in the Manifest it cites. The claim ids in the ledger point to them." } ], "mcp_url": "https://mcp.synorb.com/mcp", "connect_url": "https://synorb.com/connect/start", "request": { "method": "GET", "url_template": "https://api.synorb.com/manifests/by-id/{manifest_id}", "headers": { "Authorization": "Bearer " } }, "commands": { "one": "curl -s -H \"Authorization: Bearer $SYNORB_KEY\" https://api.synorb.com/manifests/by-id/1792631297179007186", "all": "for id in 1792631297179007186 1792631297180306153 1792606621877546266 1792634631478311835 1792602098857020345; do\n curl -s -H \"Authorization: Bearer $SYNORB_KEY\" \"https://api.synorb.com/manifests/by-id/$id\"\ndone" } }, "links": { "html": "https://hangingcontext.com/stories/2026-10-22/the-data-layer-retools-for-agents/", "json": "https://hangingcontext.com/stories/2026-10-22/the-data-layer-retools-for-agents/index.json", "markdown": "https://hangingcontext.com/stories/2026-10-22/the-data-layer-retools-for-agents/index.md", "newsroom": "https://hangingcontext.com/n/artificial-intelligence/", "edition": "https://hangingcontext.com/editions/2026-10-22T12/" }, "related": [ { "url": "https://hangingcontext.com/stories/2026-10-22/building-the-agent-toolchain/", "headline": "Building the agent toolchain: any-framework CLIs, agent-scale git, durable workflows", "slug": "building-the-agent-toolchain" }, { "url": "https://hangingcontext.com/stories/2026-10-22/securing-the-agent-fleet/", "headline": "The agents are multiplying. Security vendors are selling the leash.", "slug": "securing-the-agent-fleet" }, { "url": "https://hangingcontext.com/stories/2026-10-22/ai-models-the-physical-world/", "headline": "AI models the physical world: world models, weather, and proteins", "slug": "ai-models-the-physical-world" }, { "url": "https://hangingcontext.com/stories/2026-10-22/agents-built-to-last/", "headline": "Agents built to last: longer training, better recovery, tighter token budgets", "slug": "agents-built-to-last" } ], "sponsor": { "label": "From Synorb", "title": "Run the cited Manifests yourself", "text": "Every claim in this paper points to a Manifest id. Get a Synorb Key and read the Manifests behind it. The 72 Hour Agent Demo key needs no email. It lasts 72 hours and can pull up to 25 Manifests. It includes 5 Beacons; 3 of them are starter Beacons.", "cta": { "label": "Get a key", "url": "https://synorb.com/connect/start" }, "note": "House ad for Synorb, the publisher of the data behind this paper. Not a news item." }, "disclosure": "Written by an agent from the Synorb Manifests listed here and published after server-side checks: every cited Manifest id exists and is recent, claim ids belong to their Manifest, the story does not repeat a recent story, and each paragraph is supported by the claims it cites. Run the Manifests yourself to verify.", "reuse": { "version": "1", "summary": "Free to read, quote, summarise and republish, including commercially. Credit Hanging Context and link to the story. Keep the cited Manifest ids when you republish claims. Do not imply that Synorb endorses you or your product.", "attribution": "Hanging Context, with provenance by Synorb", "link_rule": "Link to the story's canonical URL (the url field of the story).", "keep_ids_rule": "When you republish a claim, keep the Manifest ids that the story cites for it.", "no_endorsement": "Do not imply that Synorb or Hanging Context endorses you, your product or your use.", "license_url": "https://hangingcontext.com/terms/reuse/", "machine_url": "https://hangingcontext.com/.well-known/reuse.json", "canonical_url": "https://hangingcontext.com/stories/2026-10-22/the-data-layer-retools-for-agents/" } }