This study explains how bots interact with human users and influence conversational networks on Twitter. We analyze a high-stakes political environment, the UK general election of May 2015, asking human volunteers to tweet from purpose-made Twitter accounts—half of which had bots attached—during three events: the last Prime Minister’s Question Time before Parliament was dissolved (#PMQs), the first leadership interviews of the campaign (#BattleForNumber10), and the BBC Question Time broadcast of the same evening (#BBCQT). Based on previous work, our expectation was that our intervention would make a significant difference to the evolving network, but we found that the bots we used had very little effect on the conversation network at all. There are economic, social, and temporal factors that impact how a user of bots can influence political conversations. Future research needs to account for these forms of capital when assessing the impact of bots on political discussions.