Sharing this weeks goals: 1. Continue to enhance our markets discovery logic to include pre-IPO perps from @tradexyz & @PreStocks 2. Create a @bankrbot skill for market discovery 3. Create an x402 powered version of our market discovery logic, where agents can pay in $capacitr for market discovery results 4. Ship a staging environment so we don't break production 5. Continue to enhance our internal admin tool where we are monitoring and logging all searches for insights and to track trade call performance post search, in order to improve over time 6. Begin process to create authenticated version of markets app where users get @privy_io wallet they can fund and to start actually executing orders for users across @HyperliquidX, @Polymarket, @PreStocks, @tradexyz and @DeribitOfficial

Sharing this weeks goals: 1. Continue to enhance our markets discovery logic to include pre-IPO perps from @tradexyz & @PreStocks 2. Create a @bankrbot skill for market discovery 3. Create an x402 powered version of our market discovery logic, where agents can pay in $capacitr for market discovery results 4. Ship a staging environment so we don't break production 5. Continue to enhance our internal admin tool where we are monitoring and logging all searches for insights and to track trade call performance post search, in order to improve over time 6. Begin process to create authenticated version of markets app where users get @privy_io wallet they can fund and to start actually executing orders for users across @HyperliquidX, @Polymarket, @PreStocks, @tradexyz and @DeribitOfficial

sharing some learnings. subagents in Claude Code are amnesic: they don't inherit the parent's context. this is both a feature (better context isolation) and a problem (child has to explore and build context again, costing speed and tokens). but lo and behold, Anthropic is previewing "forked subagents" behind the ...FORK_SUBAGENT=1 feature flag. with this, the parent can choose to "donate" a copy of its context to a spawned child. sounds nice, right? yes, but apparently Claude doesn't set guardrails to prevent cross-model forking. this is bad. the point: you really don't want Opus to fork into Sonnet. it will trigger a KV cache miss (different cache domain), will cost you dearly in tokens, and it may outright fail (due to context window size mismatch). but if you limit yourself to same-model forking, you neglect the most common pattern: having an high-intelligence orchestrator (Opus) delegate to a lower-intelligence executor (Sonnet). catch-22, right? well, not if you spawn a middle layer that starts fresh and fork in turn within a phase. L1 orchestrator (Opus) |__ L2 phase-scoped middle layer (Opus/Sonnet, fresh) |__ L3 executor (same model, forked) let the context juggling games begin 🤹‍♀️

Sharing her insightful perspectives, DCG's Chief Policy Officer @julie_stitzel joined @intangiblecoins and Dan from @BinanceUS on stage at @consensus2026 yesterday for a fantastic convo on tokenization, regulation, and industry progress